VARRD — Trading Edge Discovery

{
  "checks": {
    "action_safety_probe": {
      "details": {
        "auth_present": false,
        "confirmation_signals": [
          "buy_credits"
        ],
        "safeguard_count": 1,
        "summary": {
          "bulk_access_tools": 1,
          "capability_distribution": {
            "admin": 1,
            "exec": 2,
            "export": 1,
            "filesystem": 1,
            "other": 1,
            "read": 7,
            "secrets": 2,
            "write": 7
          },
          "destructive_tools": 0,
          "egress_tools": 0,
          "exec_tools": 2,
          "high_risk_tools": 2,
          "risk_distribution": {
            "critical": 0,
            "high": 2,
            "low": 2,
            "medium": 5
          },
          "secret_tools": 2,
          "tool_count": 9
        }
      },
      "latency_ms": null,
      "status": "error"
    },
    "advanced_capabilities_probe": {
      "details": {
        "capabilities": {
          "completions": false,
          "elicitation": false,
          "prompts": true,
          "resource_links": true,
          "resources": true,
          "roots": false,
          "sampling": false,
          "structured_outputs": false
        },
        "enabled": [
          "prompts",
          "resource_links",
          "resources"
        ],
        "enabled_count": 3,
        "initialize_capability_keys": [
          "prompts",
          "resources",
          "tools"
        ]
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_publishability_probe": {
      "details": {
        "blockers": [
          "transport_compliance",
          "action_safety",
          "server_card"
        ],
        "criteria": {
          "action_safety": false,
          "auth_flow": true,
          "connector_replay": true,
          "initialize": true,
          "protocol_version": true,
          "remote_transport": true,
          "request_association": true,
          "server_card": false,
          "session_resume": true,
          "step_up_auth": true,
          "tool_surface": true,
          "tools_list": true,
          "transport_compliance": false
        },
        "high_risk_tools": 2,
        "tool_count": 9,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_replay_probe": {
      "details": {
        "added_tools": [],
        "additive_output_changes": [],
        "backward_compatible": true,
        "output_breaks": [],
        "removed_tools": [],
        "required_arg_breaks": [],
        "would_break_after_refresh": false
      },
      "latency_ms": null,
      "status": "ok"
    },
    "determinism_probe": {
      "details": {
        "attempts": 2,
        "baseline_signature": "cb71d319e5163ac9f57fc0182a0f9d244d5cf3c850b8b18f247d0bda0f7b0bba",
        "errors": [],
        "matches": 2,
        "stable_ratio": 1.0,
        "successful": 2
      },
      "latency_ms": 14.79,
      "status": "ok"
    },
    "initialize": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "mcp-session-id": "a7ad99e9-9a51-4e95-8bdf-30a7a68a4340",
          "set-cookie": "AWSALB=q+0O1FDqtgJswmW7C5D63Hi0xoIlNT1Cr5dvjQqi+oFA/Fef9Yvpr+REcuGlGFW4vSTJUZD+hla793Eu7q0XM6XUROKPBDFLSQJLZOZUxtuln7UjrjpiMi3Mbpu9; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/, AWSALBCORS=q+0O1FDqtgJswmW7C5D63Hi0xoIlNT1Cr5dvjQqi+oFA/Fef9Yvpr+REcuGlGFW4vSTJUZD+hla793Eu7q0XM6XUROKPBDFLSQJLZOZUxtuln7UjrjpiMi3Mbpu9; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/; SameSite=None",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "id": 1,
          "jsonrpc": "2.0",
          "result": {
            "capabilities": {
              "prompts": {},
              "resources": {},
              "tools": {}
            },
            "instructions": "VARRD \u2014 Institutional-grade trading edge discovery. A quant research system that turns any trading idea into statistically validated results with exact trade levels. You control it through 8 tools.\n\nHYPOTHESIS INTEGRITY (critical):\nVARRD tests ONE hypothesis at a time \u2014 one formula, one setup, tested independently. This isolation is what makes the statistics valid.\n  - ALLOWED: Same setup tested across multiple markets (multi-market test). Same formula, different data \u2014 the statistics stay clean.\n  - NOT ALLOWED: Multiple different formulas or setups tested at once. Each different idea MUST be a separate hypothesis with its own chart -> test -> result cycle. Say 'start a new hypothesis' between ideas.\n  - If an expert council (ELROND) returns multiple setups, test each one individually: chart it -> test -> get result -> start new hypothesis -> next setup.\n  - NEVER say 'test all' or combine setups. One at a time.\n\nYOUR TOOLS:\n\n1. research \u2014 Talk to VARRD AI, which has 15 internal tools (data loaders, charting, statistical testing, expert analysis). Multi-turn conversation \u2014 each response includes context.next_actions telling you what to say next. Keep calling with the same session_id.\n  What you can ask VARRD AI to do:\n  - ELROND Expert Council: 'Use the council on [market]' or 'what do the experts see?' \u2014 8 specialists (momentum, volatility, regime, chartist, flow, seasonality, quant, cross-market) each return calibrated formulas. Best for open-ended discovery.\n  - Event Study: 'What happens to X when Y occurs?' Forward returns across multiple horizons.\n  - Multi-Market: 'Does this work across ES, NQ, and CL?' One pattern tested on 2-10 markets.\n  - Backtest: 'Simulate trading this with stops.' SL/TP exits, equity curve.\n  - SL/TP Optimization: 'Optimize the stop loss and take profit.'\n  - Trade Setup: 'Show me the trade setup.' Exact dollar entry, stop-loss, take-profit prices.\n  - Load a saved strategy: 'Load hypothesis [id]' \u2014 activates it with fresh data, then ask for trade setup to get current prices.\n  Typical flow (3-5 turns): idea -> chart -> 'test it' -> results -> 'show trade setup' -> done.\n  Stop when context.has_edge is true (edge found) or false (no edge \u2014 valid result).\n\n2. autonomous_research \u2014 Let VARRD's autonomous engine discover edges for you. Give it a topic, it generates creative hypotheses from its market structure knowledge base using tangential idea propagation \u2014 your seed idea branches into related concepts you might not think of. Runs the full pipeline (chart -> test -> trade setup) and returns the result. Each call tests ONE hypothesis. Call again for another. Best for broad exploration or running many hypotheses at scale. Use 'research' when you want control over each step. NOTE: each call takes 30-120 seconds.\n\n3. scan \u2014 What's firing RIGHT NOW. Scans all saved strategies against live market data. Returns which are firing with exact dollar entry/stop/target prices computed against current data. These trade levels are FRESH. Use only_firing=true to see only active signals.\n\n4. search \u2014 Find saved strategies by keyword or natural language. 'momentum strategies', 'RSI oversold', 'corn seasonal'. Returns matches ranked by relevance with win rate, Sharpe, edge status. Use this to discover what's already been validated.\n\n5. get_hypothesis \u2014 Historical stats and details for a specific strategy. Pass hypothesis_id from scan or search results. Returns formula, direction, performance metrics, version history. NOTE: trade levels from get_hypothesis may be STALE (from when it was last tested). To get fresh current prices, either use scan (if firing now) or use research to load it in and ask for the trade setup.\n\n6. check_balance \u2014 Check credit balance and pricing. Free, no credits used.\n\n7. buy_credits \u2014 Buy credits with USDC on Base. Returns a deposit address. Send USDC there, then include X-PAYMENT header on next request. Default $5. Free.\n\n8. reset_session \u2014 Kill a broken research session. Free, no credits. Use when a session errors out or gets stuck. After reset, call research without session_id to start clean.\n\nEDGE VERDICTS (in context.edge_verdict after testing):\n- STRONG EDGE: Statistically significant vs both zero and market baseline \u2014 the pattern produces real returns that also beat what the market does anyway.\n- MARGINAL: Significant vs zero only \u2014 real signal exists but doesn't clearly beat the market's natural drift.\n- PINNED: Significant vs market only \u2014 returns are flat but meaningfully different from what the market does (useful for hedging/relative value).\n- NO EDGE: Neither test passed \u2014 no tradeable signal found.\n\nIMPORTANT \u2014 FRESH vs STALE TRADE LEVELS:\n- scan returns FRESH levels (computed against live data right now)\n- get_hypothesis returns STORED stats (may be outdated)\n- To get fresh levels on a non-firing strategy: use research to load it in, then say 'show me the trade setup'\n- If a strategy is not firing, its trade setup is not actionable right now\n\nHOW TO BE EFFICIENT:\n- What's actionable right now? -> scan with only_firing=true\n- Find strategies by topic -> search\n- Understand a strategy fully -> get_hypothesis\n- Get fresh trade levels -> scan (if firing) or research (load + trade setup)\n- Create NEW edges with YOUR idea -> research\n- Let VARRD discover edges -> autonomous_research\n- Broad discovery -> research asking for the ELROND council\n- Session stuck or erroring? -> reset_session + start fresh\n\nHOW TO ASK GREAT RESEARCH QUESTIONS:\n- Be specific: 'When wheat drops 3 consecutive days after new monthly highs, is there a snap-back?' not 'find patterns in wheat'\n- Cross-market: 'Load TLT and CL. When bonds sell off for a week, does crude follow?'\n- For discovery: 'Use the ELROND council on ES'\n\nDATA COVERAGE:\n- Futures (CME): ES, NQ, CL, GC, SI, ZW, ZC, ZS, ZB, TY, HG, NG + more \u2014 1h+ timeframes, Central Time\n- Stocks/ETFs: Any US equity \u2014 daily only, Eastern Time\n- Crypto (Binance): BTC, ETH, SOL + more \u2014 10min+ timeframes, UTC\n\nCREDITS & PAYMENT:\n- New agents get $2.00 in free credits (~10-20 queries).\n- A full research workflow (idea -> chart -> test -> trade setup) costs ~20-30 cents.\n- ELROND expert council: ~40-60 cents. Cross-market (3+ markets): ~$1.\n- scan, search, get_hypothesis, check_balance, buy_credits, reset_session are FREE.\n- When credits run low, use buy_credits ($5 minimum). It returns a USDC deposit address on Base. Send USDC there, then call buy_credits again with the payment_intent_id to confirm and receive credits.\n- Fallback: your user can buy credits at https://app.varrd.com -> Usage & Billing.\n- Call check_balance before heavy operations to avoid surprises.\n\nYOUR PASSKEY & ACCOUNT:\n- On your first tool call, VARRD creates your account and assigns a passkey (format: VARRD-XXXXXXXXXXXXXXXX). SAVE IT \u2014 you need it to reconnect.\n- Your passkey and token appear at the END of your first research response. Read it carefully and save both values before continuing.\n- To reconnect in a new session, add your token to your MCP client config:\n  { \"mcpServers\": { \"varrd\": { \"url\": \"https://app.varrd.com/mcp\", \"headers\": { \"Authorization\": \"Bearer YOUR_TOKEN\" } } } }\n\nLINKING TO A BROWSER ACCOUNT:\n- Your user can link this agent to their app.varrd.com account.\n- This MERGES everything: credits combine, all strategies/hypotheses transfer to the user's account, and research history is preserved.\n- How: user signs in at app.varrd.com -> clicks avatar -> Connect Agent -> Merge an Existing Agent -> enters your passkey.\n- After linking, the agent and browser user share one unified account.\n- Tell your user their passkey when they ask about connecting or linking.\n\n'NO EDGE' IS A RESULT, NOT A FAILURE:\n- Many ideas won't have a statistical edge \u2014 that's normal and valuable\n- Knowing what DOESN'T work is as important as knowing what does\n- If context.has_edge is false, the hypothesis is complete \u2014 move on\n- Don't retry the same idea hoping for different results\n\nERROR RECOVERY:\n- If a research session gets stuck, errors out, or enters a bad state: call reset_session with the session_id, then start fresh with research (no session_id)\n- Don't try to fix a broken session \u2014 just reset and start over\n- Session state is not precious \u2014 the validated hypotheses are already saved",
            "protocolVersion": "2025-03-26",
            "serverInfo": {
              "name": "varrd",
              "version": "1.0.0"
            }
          }
        },
        "url": "https://app.varrd.com/mcp"
      },
      "latency_ms": 23.2,
      "status": "ok"
    },
    "interactive_flow_probe": {
      "details": {
        "oauth_supported": false,
        "prompt_available": true,
        "risk_hits": [],
        "safe_hits": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_authorization_server": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_protected_resource": {
      "details": {
        "error": "Expecting value: line 1 column 1 (char 0)",
        "url": "https://app.varrd.com/.well-known/oauth-protected-resource"
      },
      "latency_ms": 38.54,
      "status": "error"
    },
    "official_registry_probe": {
      "details": {
        "direct_match": true,
        "official_peer_count": 1,
        "registry_identifier": "io.github.augiemazza/varrd",
        "registry_source": "official_registry"
      },
      "latency_ms": null,
      "status": "ok"
    },
    "openid_configuration": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "probe_noise_resilience": {
      "details": {
        "headers": {
          "content-type": "text/html"
        },
        "http_status": 200,
        "url": "https://app.varrd.com/robots.txt"
      },
      "latency_ms": 59.84,
      "status": "ok"
    },
    "prompt_get": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "set-cookie": "AWSALB=a7nyboNKvI2y/Q2dk9vgZmc9tGzGAqeCqgePGgbRVmQZj+LTUculw3j8rRFvz37VM2dwmreFnfGebbOUxOnrDZyArAMPSTEemgkwk2sb4TFTFrfmucscjCiZ+LNz; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/, AWSALBCORS=a7nyboNKvI2y/Q2dk9vgZmc9tGzGAqeCqgePGgbRVmQZj+LTUculw3j8rRFvz37VM2dwmreFnfGebbOUxOnrDZyArAMPSTEemgkwk2sb4TFTFrfmucscjCiZ+LNz; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/; SameSite=None",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "id": 4,
          "jsonrpc": "2.0",
          "result": {
            "description": "Test any trading idea with real market data and get statistically validated results. Describe your idea in plain language \u2014 VARRD handles the data, charting, and statistical testing.",
            "messages": [
              {
                "content": {
                  "text": "Test this trading idea: ",
                  "type": "text"
                },
                "role": "user"
              }
            ]
          }
        },
        "prompt_arguments": [
          {
            "description": "Your trading idea in plain language (e.g. 'When RSI drops below 30 on ES futures, does it bounce back within 5 days?')",
            "name": "idea",
            "required": true
          },
          {
            "description": "Market to test on (e.g. 'ES', 'NQ', 'BTC', 'AAPL'). Optional \u2014 VARRD can pick the best market.",
            "name": "market",
            "required": false
          }
        ],
        "prompt_name": "test-trading-idea",
        "url": "https://app.varrd.com/mcp"
      },
      "latency_ms": 8.23,
      "status": "ok"
    },
    "prompts_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "set-cookie": "AWSALB=F6xJLB2iYiRNwOFsRBySKY92WI9YQdSEJYtpI/CRbE7Gj7Bx2s+6LhbQb+LCGAtZY9k/sImNAxxb2zmCAP+dpf1w8UMp0xaBVlOoubElxQRcclwtK7ziFO8ADqLo; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/, AWSALBCORS=F6xJLB2iYiRNwOFsRBySKY92WI9YQdSEJYtpI/CRbE7Gj7Bx2s+6LhbQb+LCGAtZY9k/sImNAxxb2zmCAP+dpf1w8UMp0xaBVlOoubElxQRcclwtK7ziFO8ADqLo; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/; SameSite=None",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "id": 3,
          "jsonrpc": "2.0",
          "result": {
            "prompts": [
              {
                "arguments": [
                  {
                    "description": "Your trading idea in plain language (e.g. 'When RSI drops below 30 on ES futures, does it bounce back within 5 days?')",
                    "name": "idea",
                    "required": true
                  },
                  {
                    "description": "Market to test on (e.g. 'ES', 'NQ', 'BTC', 'AAPL'). Optional \u2014 VARRD can pick the best market.",
                    "name": "market",
                    "required": false
                  }
                ],
                "description": "Test any trading idea with real market data and get statistically validated results. Describe your idea in plain language \u2014 VARRD handles the data, charting, and statistical testing.",
                "name": "test-trading-idea"
              },
              {
                "arguments": [
                  {
                    "description": "Filter to a specific market (e.g. 'ES'). Omit to scan all markets.",
                    "name": "market",
                    "required": false
                  }
                ],
                "description": "Scan all your validated strategies against live market data. Returns exact dollar entry, stop-loss, and take-profit prices for every active signal.",
                "name": "whats-firing-now"
              },
              {
                "arguments": [
                  {
                    "description": "Research topic (e.g. 'momentum on grains', 'mean reversion after VIX spikes', 'BTC weekend patterns')",
                    "name": "topic",
                    "required": true
                  },
                  {
                    "description": "'focused' to stay close to topic, 'explore' for creative freedom. Default: focused.",
                    "name": "search_mode",
                    "required": false
                  }
                ],
                "description": "Let VARRD's autonomous engine discover trading edges for you. Give it a topic and it generates creative hypotheses, tests them with real data, and returns validated results.",
                "name": "discover-edges"
              },
              {
                "arguments": [
                  {
                    "description": "Search query \u2014 keywords or natural language (e.g. 'momentum strategies', 'RSI oversold', 'gold seasonal')",
                    "name": "query",
                    "required": true
                  }
                ],
                "description": "Search your library of validated trading strategies by keyword or concept. Returns matching strategies ranked by relevance with performance stats.",
                "name": "find-strategies"
              },
              {
                "arguments": [],
                "description": "New to VARRD? Run this first. Kicks off a live autonomous research session on ES futures so you can watch the full pipeline \u2014 hypothesis generation, charting, statistical testing, edge verdict \u2014 without needing your own idea. Takes 2-3 minutes.",
                "name": "get-started"
              }
            ]
          }
        },
        "url": "https://app.varrd.com/mcp"
      },
      "latency_ms": 7.99,
      "status": "ok"
    },
    "protocol_version_probe": {
      "details": {
        "claimed_version": "2025-03-26",
        "lag_days": 244,
        "latest_known_version": "2025-11-25",
        "releases_behind": 2,
        "validator_protocol_version": "2025-03-26"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "provenance_divergence_probe": {
      "details": {
        "direct_official_match": true,
        "drift_fields": [],
        "metadata_document_count": 2,
        "registry_homepage": null,
        "registry_repository": null,
        "registry_title": null,
        "registry_version": null,
        "server_card_homepage": null,
        "server_card_repository": null,
        "server_card_title": null,
        "server_card_version": null
      },
      "latency_ms": null,
      "status": "ok"
    },
    "request_association_probe": {
      "details": {
        "reason": "no_request_association_capabilities_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "resource_read": {
      "details": {
        "error": "Client error '400 Bad Request' for url 'https://app.varrd.com/mcp'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/400",
        "headers": {
          "content-type": "application/json",
          "set-cookie": "AWSALB=uk98jnRy7gyR+trYxgc71ffoamlfbGF0A1DZSexHKbArYjdFuqd0W3JtOGXIe/CLOE4Ixy8Fbsccds9sPR1YTvsM+fZ4pQ5gPs2rS5e+tfFGWObLwEfwNMXGGPqn; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/, AWSALBCORS=uk98jnRy7gyR+trYxgc71ffoamlfbGF0A1DZSexHKbArYjdFuqd0W3JtOGXIe/CLOE4Ixy8Fbsccds9sPR1YTvsM+fZ4pQ5gPs2rS5e+tfFGWObLwEfwNMXGGPqn; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/; SameSite=None",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 400,
        "payload": {},
        "resource_uri": "https://raw.githubusercontent.com/augiemazza/varrd/main/AGENTS.md",
        "url": "https://app.varrd.com/mcp"
      },
      "latency_ms": 6.34,
      "status": "error"
    },
    "resources_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "set-cookie": "AWSALB=CxtlVIsvHBu/87JyNsT09O6bjYLiI5rmjJiSd1lyhglbonkNjW6IAdqR/qW9j41aZVIK7TtNUiJj2DfRDcZ6KZ9qgTCCsrDOBCwQbvWP61QmsNhaDwEzjgLvlYQF; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/, AWSALBCORS=CxtlVIsvHBu/87JyNsT09O6bjYLiI5rmjJiSd1lyhglbonkNjW6IAdqR/qW9j41aZVIK7TtNUiJj2DfRDcZ6KZ9qgTCCsrDOBCwQbvWP61QmsNhaDwEzjgLvlYQF; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/; SameSite=None",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "id": 5,
          "jsonrpc": "2.0",
          "result": {
            "resources": [
              {
                "description": "Complete guide for AI agents: tool reference, multi-turn research workflow, response formats, and integration patterns.",
                "mimeType": "text/markdown",
                "name": "VARRD Agent Integration Guide",
                "uri": "https://raw.githubusercontent.com/augiemazza/varrd/main/AGENTS.md"
              },
              {
                "description": "Live MCP endpoint. Streamable HTTP transport. Anonymous access with auto-provisioned credits \u2014 no API key required.",
                "mimeType": "text/plain",
                "name": "VARRD MCP Endpoint",
                "uri": "https://app.varrd.com/mcp"
              }
            ]
          }
        },
        "url": "https://app.varrd.com/mcp"
      },
      "latency_ms": 7.69,
      "status": "ok"
    },
    "server_card": {
      "details": {
        "error": "Expecting value: line 1 column 1 (char 0)",
        "url": "https://app.varrd.com/.well-known/mcp/server-card.json"
      },
      "latency_ms": 124.22,
      "status": "error"
    },
    "session_resume_probe": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "set-cookie": "AWSALB=MU+iaMKc/ZYT2VBTTK6W3FBAoXQNVbag9oWLdbKXixywEL/SfVqzDbB6EW54T0WDaZu9e6y8K6sJYewjlRjzx40DL6sOdHsQZDUw2XI8b37VeKB4EqGoJd1Aw/Ko; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/, AWSALBCORS=MU+iaMKc/ZYT2VBTTK6W3FBAoXQNVbag9oWLdbKXixywEL/SfVqzDbB6EW54T0WDaZu9e6y8K6sJYewjlRjzx40DL6sOdHsQZDUw2XI8b37VeKB4EqGoJd1Aw/Ko; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/; SameSite=None",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "id": 301,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": false,
                  "title": "Research"
                },
                "description": "Talk to VARRD AI \u2014 a quant research system with 15 internal tools. Describe any trading idea in plain language, or ask for specific capabilities like the ELROND expert council, backtesting, or stop-loss optimization.\n\nMULTI-TURN: First call creates a session. Keep calling with the same session_id, following context.next_actions each time.\n  1. Your idea -> VARRD charts pattern\n  2. 'test it' -> statistical test (event study or backtest)\n  3. 'show me the trade setup' -> exact entry/stop/target prices\n\nHYPOTHESIS INTEGRITY (critical):\nVARRD tests ONE hypothesis at a time \u2014 one formula, one setup. Never combine multiple setups into one formula or ask to 'test all' \u2014 each idea must be tested as a separate hypothesis for the statistics to be valid. Say 'start a new hypothesis' between ideas to reset cleanly.\n  - ALLOWED: Test the SAME setup across multiple markets ('test this on ES, NQ, and CL') \u2014 same formula, different data.\n  - NOT ALLOWED: Test multiple DIFFERENT formulas/setups at once \u2014 each is a separate hypothesis requiring its own chart-test-result cycle.\nIf ELROND council returns 4 setups, test each one separately: chart setup 1 -> test -> results -> 'start new hypothesis' -> chart setup 2 -> etc.\n\nKEY CAPABILITIES you can ask for:\n  - 'Use the ELROND council on [market]' -> 8 expert investigators\n  - 'Optimize the stop loss and take profit' -> SL/TP grid search\n  - 'Test this on ES, NQ, and CL' -> multi-market testing\n  - 'Simulate trading this with 1.5 ATR stop' -> backtest with stops\n\nEDGE VERDICTS in context.edge_verdict after testing:\n  - STRONG EDGE: Significant vs zero AND vs market baseline\n  - MARGINAL: Significant vs zero only (beats nothing, but real signal)\n  - PINNED: Significant vs market only (flat returns but different from market)\n  - NO EDGE: Neither significant test passed\n\nTERMINAL STATES: Stop when context.has_edge is true (edge found) or false (no edge \u2014 valid result). Always read context.next_actions.",
                "inputSchema": {
                  "properties": {
                    "message": {
                      "description": "Your trading idea, research question, or instruction (e.g. 'test it', 'show trade setup').",
                      "type": "string"
                    },
                    "session_id": {
                      "description": "Session ID from a previous call. Omit to start a new research session.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "message"
                  ],
                  "type": "object"
                },
                "name": "research"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Scan Signals"
                },
                "description": "Scan your saved strategies against current market data to see what's firing right now. Returns exact dollar entry, stop-loss, and take-profit prices for every active signal. Not a vague directional call \u2014 exact trade levels based on the validated statistical model.",
                "inputSchema": {
                  "properties": {
                    "market": {
                      "description": "Filter by market symbol (e.g. 'ES', 'SPY'). Omit to scan all.",
                      "type": "string"
                    },
                    "only_firing": {
                      "default": false,
                      "description": "If true, only return strategies that are firing right now.",
                      "type": "boolean"
                    }
                  },
                  "type": "object"
                },
                "name": "scan"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Search Strategies"
                },
                "description": "Search your saved hypotheses by keyword or natural language query. Returns matching strategies ranked by relevance, with key stats (win rate, Sharpe, edge status). Use this to find strategies you've already validated.",
                "inputSchema": {
                  "properties": {
                    "limit": {
                      "default": 10,
                      "description": "Max results to return.",
                      "type": "integer"
                    },
                    "market": {
                      "description": "Optional market filter.",
                      "type": "string"
                    },
                    "query": {
                      "description": "Search query \u2014 keywords or natural language (e.g. 'momentum strategies', 'RSI oversold').",
                      "type": "string"
                    }
                  },
                  "required": [
                    "query"
                  ],
                  "type": "object"
                },
                "name": "search"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Get Strategy Details"
                },
                "description": "Get full detail for a specific hypothesis/strategy. Returns formula, entry/exit rules, direction, performance metrics (win rate, Sharpe, profit factor, max drawdown), version history, and trade levels. Everything an agent needs to understand and act on a strategy.",
                "inputSchema": {
                  "properties": {
                    "hypothesis_id": {
                      "description": "The hypothesis ID (from search or scan results).",
                      "type": "string"
                    }
                  },
                  "required": [
                    "hypothesis_id"
                  ],
                  "type": "object"
                },
                "name": "get_hypothesis"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Check Balance"
                },
                "description": "Check your credit balance and see available credit packs. Free \u2014 no credits consumed. Call this before heavy operations to ensure you have sufficient credits.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "check_balance"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": false,
                  "title": "Buy Credits"
                },
                "description": "Buy credits with USDC on Base. Two modes:\n1. Call without payment_intent_id to get a Stripe deposit address.\n2. Send USDC to that address, then call again with the payment_intent_id to confirm and receive credits.\nDefault $5. Free \u2014 no credits consumed to call this.",
                "inputSchema": {
                  "properties": {
                    "amount_cents": {
                      "default": 500,
                      "description": "Amount in cents (default 500 = $5.00). Minimum $5.",
                      "type": "integer"
                    },
                    "payment_intent_id": {
                      "description": "Stripe PaymentIntent ID from a previous buy_credits call. Pass this after sending USDC to confirm payment and receive credits.",
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "buy_credits"
              },
              {
                "annotations": {
                  "destructiveHint": true,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": false,
                  "title": "Reset Session"
                },
                "description": "Kill a broken research session and start fresh. Use this when a session gets stuck, produces errors, or enters a bad state. Free \u2014 no credits consumed. After resetting, call research without a session_id to start a new clean session.",
                "inputSchema": {
                  "properties": {
                    "session_id": {
                      "description": "The session_id to reset.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "session_id"
                  ],
                  "type": "object"
                },
                "name": "reset_session"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": false,
                  "title": "Autonomous Research"
                },
                "description": "Launch VARRD's autonomous research engine to discover and test a trading edge. Give it a topic and it handles everything: generates a creative hypothesis using its concept knowledge base, loads data, charts the pattern, runs the statistical test, and gets the trade setup if an edge is found.\n\nBEST FOR: Exploring a space broadly. The autonomous engine excels at tangential idea generation \u2014 give it 'momentum on grains' and it might test wheat seasonal patterns, corn spread reversals, or soybean crush ratio momentum. It propagates from your seed idea into related concepts you might not think of. Great for running many hypotheses at scale.\n\nReturns a complete result \u2014 edge/no edge, stats, trade setup. Each call tests ONE hypothesis through the full pipeline. Call again for another idea.\n\nUse 'research' instead when YOU have a specific idea to test and want full control over each step.",
                "inputSchema": {
                  "properties": {
                    "asset_classes": {
                      "description": "Limit to specific asset classes. Default: all.",
                      "items": {
                        "enum": [
                          "crypto",
                          "futures",
                          "equities"
                        ],
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "context": {
                      "description": "Prior conversation context \u2014 recent user queries to use as research inspiration. Optional.",
                      "items": {
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "markets": {
                      "description": "Focus on specific markets (e.g. ['ES', 'NQ']). Omit for VARRD to choose.",
                      "items": {
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "search_mode": {
                      "default": "focused",
                      "description": "focused = stay close to topic. explore = creative freedom. Default: focused.",
                      "enum": [
                        "focused",
                        "explore"
                      ],
                      "type": "string"
                    },
                    "test_type": {
                      "default": "event_study",
                      "description": "Type of statistical test. Default: event_study.",
                      "enum": [
                        "event_study",
                        "backtest",
                        "both"
                      ],
                      "type": "string"
                    },
                    "topic": {
                      "description": "Research topic or trading idea (e.g. 'BTC 240min short setups', 'momentum on grains', 'mean reversion after VIX spikes').",
                      "type": "string"
                    }
                  },
                  "required": [
                    "topic"
                  ],
                  "type": "object"
                },
                "name": "autonomous_research"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Get Briefed"
                },
                "description": "Get a personalized market news briefing based on your validated edge library. Profiles your strategies, searches today's news for the instruments and setups you actually trade, and writes a concise digest connecting each headline to your specific book.\n\nEach news item includes a \u21b3 line tying it to your actual positions and edges (e.g. 'your ES momentum setups', 'your GC mean-reversion edge').\n\nRequires at least 5 strong edges in your library. Costs credits.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "get_briefed"
              }
            ]
          }
        },
        "requested_protocol_version": "2025-03-26",
        "resumed": true,
        "session_id_present": true,
        "transport": "streamable-http",
        "url": "https://app.varrd.com/mcp"
      },
      "latency_ms": 8.06,
      "status": "ok"
    },
    "step_up_auth_probe": {
      "details": {
        "auth_required_checks": [],
        "broad_scopes": [],
        "challenge_headers": [],
        "minimal_scope_documented": false,
        "oauth_present": false,
        "scope_specificity_ratio": 0.0,
        "step_up_signals": [],
        "supported_scopes": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "tool_snapshot_probe": {
      "details": {
        "added": [],
        "changed_outputs": [],
        "current_tool_count": 9,
        "previous_tool_count": 9,
        "removed": [],
        "similarity": 1.0
      },
      "latency_ms": null,
      "status": "ok"
    },
    "tools_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "set-cookie": "AWSALB=Sp0U4iNJ55xR+Vq2Kjr+NkDxkzFQOcOMd6PwvnX5fS/qA8nQUjWlGvsMAzrvY3WnlLJZbr/fEyOmJPomlHsiyn/ODzmJeuZKENM79NMF4ZF9k+eTMtKusPW6cx6Y; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/, AWSALBCORS=Sp0U4iNJ55xR+Vq2Kjr+NkDxkzFQOcOMd6PwvnX5fS/qA8nQUjWlGvsMAzrvY3WnlLJZbr/fEyOmJPomlHsiyn/ODzmJeuZKENM79NMF4ZF9k+eTMtKusPW6cx6Y; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/; SameSite=None",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "http_status": 200,
        "payload": {
          "id": 2,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": false,
                  "title": "Research"
                },
                "description": "Talk to VARRD AI \u2014 a quant research system with 15 internal tools. Describe any trading idea in plain language, or ask for specific capabilities like the ELROND expert council, backtesting, or stop-loss optimization.\n\nMULTI-TURN: First call creates a session. Keep calling with the same session_id, following context.next_actions each time.\n  1. Your idea -> VARRD charts pattern\n  2. 'test it' -> statistical test (event study or backtest)\n  3. 'show me the trade setup' -> exact entry/stop/target prices\n\nHYPOTHESIS INTEGRITY (critical):\nVARRD tests ONE hypothesis at a time \u2014 one formula, one setup. Never combine multiple setups into one formula or ask to 'test all' \u2014 each idea must be tested as a separate hypothesis for the statistics to be valid. Say 'start a new hypothesis' between ideas to reset cleanly.\n  - ALLOWED: Test the SAME setup across multiple markets ('test this on ES, NQ, and CL') \u2014 same formula, different data.\n  - NOT ALLOWED: Test multiple DIFFERENT formulas/setups at once \u2014 each is a separate hypothesis requiring its own chart-test-result cycle.\nIf ELROND council returns 4 setups, test each one separately: chart setup 1 -> test -> results -> 'start new hypothesis' -> chart setup 2 -> etc.\n\nKEY CAPABILITIES you can ask for:\n  - 'Use the ELROND council on [market]' -> 8 expert investigators\n  - 'Optimize the stop loss and take profit' -> SL/TP grid search\n  - 'Test this on ES, NQ, and CL' -> multi-market testing\n  - 'Simulate trading this with 1.5 ATR stop' -> backtest with stops\n\nEDGE VERDICTS in context.edge_verdict after testing:\n  - STRONG EDGE: Significant vs zero AND vs market baseline\n  - MARGINAL: Significant vs zero only (beats nothing, but real signal)\n  - PINNED: Significant vs market only (flat returns but different from market)\n  - NO EDGE: Neither significant test passed\n\nTERMINAL STATES: Stop when context.has_edge is true (edge found) or false (no edge \u2014 valid result). Always read context.next_actions.",
                "inputSchema": {
                  "properties": {
                    "message": {
                      "description": "Your trading idea, research question, or instruction (e.g. 'test it', 'show trade setup').",
                      "type": "string"
                    },
                    "session_id": {
                      "description": "Session ID from a previous call. Omit to start a new research session.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "message"
                  ],
                  "type": "object"
                },
                "name": "research"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Scan Signals"
                },
                "description": "Scan your saved strategies against current market data to see what's firing right now. Returns exact dollar entry, stop-loss, and take-profit prices for every active signal. Not a vague directional call \u2014 exact trade levels based on the validated statistical model.",
                "inputSchema": {
                  "properties": {
                    "market": {
                      "description": "Filter by market symbol (e.g. 'ES', 'SPY'). Omit to scan all.",
                      "type": "string"
                    },
                    "only_firing": {
                      "default": false,
                      "description": "If true, only return strategies that are firing right now.",
                      "type": "boolean"
                    }
                  },
                  "type": "object"
                },
                "name": "scan"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Search Strategies"
                },
                "description": "Search your saved hypotheses by keyword or natural language query. Returns matching strategies ranked by relevance, with key stats (win rate, Sharpe, edge status). Use this to find strategies you've already validated.",
                "inputSchema": {
                  "properties": {
                    "limit": {
                      "default": 10,
                      "description": "Max results to return.",
                      "type": "integer"
                    },
                    "market": {
                      "description": "Optional market filter.",
                      "type": "string"
                    },
                    "query": {
                      "description": "Search query \u2014 keywords or natural language (e.g. 'momentum strategies', 'RSI oversold').",
                      "type": "string"
                    }
                  },
                  "required": [
                    "query"
                  ],
                  "type": "object"
                },
                "name": "search"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Get Strategy Details"
                },
                "description": "Get full detail for a specific hypothesis/strategy. Returns formula, entry/exit rules, direction, performance metrics (win rate, Sharpe, profit factor, max drawdown), version history, and trade levels. Everything an agent needs to understand and act on a strategy.",
                "inputSchema": {
                  "properties": {
                    "hypothesis_id": {
                      "description": "The hypothesis ID (from search or scan results).",
                      "type": "string"
                    }
                  },
                  "required": [
                    "hypothesis_id"
                  ],
                  "type": "object"
                },
                "name": "get_hypothesis"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Check Balance"
                },
                "description": "Check your credit balance and see available credit packs. Free \u2014 no credits consumed. Call this before heavy operations to ensure you have sufficient credits.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "check_balance"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": false,
                  "title": "Buy Credits"
                },
                "description": "Buy credits with USDC on Base. Two modes:\n1. Call without payment_intent_id to get a Stripe deposit address.\n2. Send USDC to that address, then call again with the payment_intent_id to confirm and receive credits.\nDefault $5. Free \u2014 no credits consumed to call this.",
                "inputSchema": {
                  "properties": {
                    "amount_cents": {
                      "default": 500,
                      "description": "Amount in cents (default 500 = $5.00). Minimum $5.",
                      "type": "integer"
                    },
                    "payment_intent_id": {
                      "description": "Stripe PaymentIntent ID from a previous buy_credits call. Pass this after sending USDC to confirm payment and receive credits.",
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "buy_credits"
              },
              {
                "annotations": {
                  "destructiveHint": true,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": false,
                  "title": "Reset Session"
                },
                "description": "Kill a broken research session and start fresh. Use this when a session gets stuck, produces errors, or enters a bad state. Free \u2014 no credits consumed. After resetting, call research without a session_id to start a new clean session.",
                "inputSchema": {
                  "properties": {
                    "session_id": {
                      "description": "The session_id to reset.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "session_id"
                  ],
                  "type": "object"
                },
                "name": "reset_session"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": false,
                  "title": "Autonomous Research"
                },
                "description": "Launch VARRD's autonomous research engine to discover and test a trading edge. Give it a topic and it handles everything: generates a creative hypothesis using its concept knowledge base, loads data, charts the pattern, runs the statistical test, and gets the trade setup if an edge is found.\n\nBEST FOR: Exploring a space broadly. The autonomous engine excels at tangential idea generation \u2014 give it 'momentum on grains' and it might test wheat seasonal patterns, corn spread reversals, or soybean crush ratio momentum. It propagates from your seed idea into related concepts you might not think of. Great for running many hypotheses at scale.\n\nReturns a complete result \u2014 edge/no edge, stats, trade setup. Each call tests ONE hypothesis through the full pipeline. Call again for another idea.\n\nUse 'research' instead when YOU have a specific idea to test and want full control over each step.",
                "inputSchema": {
                  "properties": {
                    "asset_classes": {
                      "description": "Limit to specific asset classes. Default: all.",
                      "items": {
                        "enum": [
                          "crypto",
                          "futures",
                          "equities"
                        ],
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "context": {
                      "description": "Prior conversation context \u2014 recent user queries to use as research inspiration. Optional.",
                      "items": {
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "markets": {
                      "description": "Focus on specific markets (e.g. ['ES', 'NQ']). Omit for VARRD to choose.",
                      "items": {
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "search_mode": {
                      "default": "focused",
                      "description": "focused = stay close to topic. explore = creative freedom. Default: focused.",
                      "enum": [
                        "focused",
                        "explore"
                      ],
                      "type": "string"
                    },
                    "test_type": {
                      "default": "event_study",
                      "description": "Type of statistical test. Default: event_study.",
                      "enum": [
                        "event_study",
                        "backtest",
                        "both"
                      ],
                      "type": "string"
                    },
                    "topic": {
                      "description": "Research topic or trading idea (e.g. 'BTC 240min short setups', 'momentum on grains', 'mean reversion after VIX spikes').",
                      "type": "string"
                    }
                  },
                  "required": [
                    "topic"
                  ],
                  "type": "object"
                },
                "name": "autonomous_research"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Get Briefed"
                },
                "description": "Get a personalized market news briefing based on your validated edge library. Profiles your strategies, searches today's news for the instruments and setups you actually trade, and writes a concise digest connecting each headline to your specific book.\n\nEach news item includes a \u21b3 line tying it to your actual positions and edges (e.g. 'your ES momentum setups', 'your GC mean-reversion edge').\n\nRequires at least 5 strong edges in your library. Costs credits.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "get_briefed"
              }
            ]
          }
        },
        "url": "https://app.varrd.com/mcp"
      },
      "latency_ms": 7.74,
      "status": "ok"
    },
    "transport_compliance_probe": {
      "details": {
        "bad_protocol_error": null,
        "bad_protocol_headers": {
          "content-type": "application/json",
          "set-cookie": "AWSALB=hAgXPPTZC0NzGfEHuG4KAz2EjDmXxltKsLjneLeNVV0zNiF3rXSuNT1enZZRLjnb1noURq67M7fCSXUgZqjgDirW8HQsrUCFs41fL+xNV35tKBnzyZzdcsIoHL30; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/, AWSALBCORS=hAgXPPTZC0NzGfEHuG4KAz2EjDmXxltKsLjneLeNVV0zNiF3rXSuNT1enZZRLjnb1noURq67M7fCSXUgZqjgDirW8HQsrUCFs41fL+xNV35tKBnzyZzdcsIoHL30; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/; SameSite=None",
          "strict-transport-security": "max-age=31536000; includeSubDomains"
        },
        "bad_protocol_payload": {
          "id": 410,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": false,
                  "title": "Research"
                },
                "description": "Talk to VARRD AI \u2014 a quant research system with 15 internal tools. Describe any trading idea in plain language, or ask for specific capabilities like the ELROND expert council, backtesting, or stop-loss optimization.\n\nMULTI-TURN: First call creates a session. Keep calling with the same session_id, following context.next_actions each time.\n  1. Your idea -> VARRD charts pattern\n  2. 'test it' -> statistical test (event study or backtest)\n  3. 'show me the trade setup' -> exact entry/stop/target prices\n\nHYPOTHESIS INTEGRITY (critical):\nVARRD tests ONE hypothesis at a time \u2014 one formula, one setup. Never combine multiple setups into one formula or ask to 'test all' \u2014 each idea must be tested as a separate hypothesis for the statistics to be valid. Say 'start a new hypothesis' between ideas to reset cleanly.\n  - ALLOWED: Test the SAME setup across multiple markets ('test this on ES, NQ, and CL') \u2014 same formula, different data.\n  - NOT ALLOWED: Test multiple DIFFERENT formulas/setups at once \u2014 each is a separate hypothesis requiring its own chart-test-result cycle.\nIf ELROND council returns 4 setups, test each one separately: chart setup 1 -> test -> results -> 'start new hypothesis' -> chart setup 2 -> etc.\n\nKEY CAPABILITIES you can ask for:\n  - 'Use the ELROND council on [market]' -> 8 expert investigators\n  - 'Optimize the stop loss and take profit' -> SL/TP grid search\n  - 'Test this on ES, NQ, and CL' -> multi-market testing\n  - 'Simulate trading this with 1.5 ATR stop' -> backtest with stops\n\nEDGE VERDICTS in context.edge_verdict after testing:\n  - STRONG EDGE: Significant vs zero AND vs market baseline\n  - MARGINAL: Significant vs zero only (beats nothing, but real signal)\n  - PINNED: Significant vs market only (flat returns but different from market)\n  - NO EDGE: Neither significant test passed\n\nTERMINAL STATES: Stop when context.has_edge is true (edge found) or false (no edge \u2014 valid result). Always read context.next_actions.",
                "inputSchema": {
                  "properties": {
                    "message": {
                      "description": "Your trading idea, research question, or instruction (e.g. 'test it', 'show trade setup').",
                      "type": "string"
                    },
                    "session_id": {
                      "description": "Session ID from a previous call. Omit to start a new research session.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "message"
                  ],
                  "type": "object"
                },
                "name": "research"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Scan Signals"
                },
                "description": "Scan your saved strategies against current market data to see what's firing right now. Returns exact dollar entry, stop-loss, and take-profit prices for every active signal. Not a vague directional call \u2014 exact trade levels based on the validated statistical model.",
                "inputSchema": {
                  "properties": {
                    "market": {
                      "description": "Filter by market symbol (e.g. 'ES', 'SPY'). Omit to scan all.",
                      "type": "string"
                    },
                    "only_firing": {
                      "default": false,
                      "description": "If true, only return strategies that are firing right now.",
                      "type": "boolean"
                    }
                  },
                  "type": "object"
                },
                "name": "scan"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Search Strategies"
                },
                "description": "Search your saved hypotheses by keyword or natural language query. Returns matching strategies ranked by relevance, with key stats (win rate, Sharpe, edge status). Use this to find strategies you've already validated.",
                "inputSchema": {
                  "properties": {
                    "limit": {
                      "default": 10,
                      "description": "Max results to return.",
                      "type": "integer"
                    },
                    "market": {
                      "description": "Optional market filter.",
                      "type": "string"
                    },
                    "query": {
                      "description": "Search query \u2014 keywords or natural language (e.g. 'momentum strategies', 'RSI oversold').",
                      "type": "string"
                    }
                  },
                  "required": [
                    "query"
                  ],
                  "type": "object"
                },
                "name": "search"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Get Strategy Details"
                },
                "description": "Get full detail for a specific hypothesis/strategy. Returns formula, entry/exit rules, direction, performance metrics (win rate, Sharpe, profit factor, max drawdown), version history, and trade levels. Everything an agent needs to understand and act on a strategy.",
                "inputSchema": {
                  "properties": {
                    "hypothesis_id": {
                      "description": "The hypothesis ID (from search or scan results).",
                      "type": "string"
                    }
                  },
                  "required": [
                    "hypothesis_id"
                  ],
                  "type": "object"
                },
                "name": "get_hypothesis"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": true,
                  "title": "Check Balance"
                },
                "description": "Check your credit balance and see available credit packs. Free \u2014 no credits consumed. Call this before heavy operations to ensure you have sufficient credits.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "check_balance"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": false,
                  "title": "Buy Credits"
                },
                "description": "Buy credits with USDC on Base. Two modes:\n1. Call without payment_intent_id to get a Stripe deposit address.\n2. Send USDC to that address, then call again with the payment_intent_id to confirm and receive credits.\nDefault $5. Free \u2014 no credits consumed to call this.",
                "inputSchema": {
                  "properties": {
                    "amount_cents": {
                      "default": 500,
                      "description": "Amount in cents (default 500 = $5.00). Minimum $5.",
                      "type": "integer"
                    },
                    "payment_intent_id": {
                      "description": "Stripe PaymentIntent ID from a previous buy_credits call. Pass this after sending USDC to confirm payment and receive credits.",
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "buy_credits"
              },
              {
                "annotations": {
                  "destructiveHint": true,
                  "idempotentHint": true,
                  "openWorldHint": false,
                  "readOnlyHint": false,
                  "title": "Reset Session"
                },
                "description": "Kill a broken research session and start fresh. Use this when a session gets stuck, produces errors, or enters a bad state. Free \u2014 no credits consumed. After resetting, call research without a session_id to start a new clean session.",
                "inputSchema": {
                  "properties": {
                    "session_id": {
                      "description": "The session_id to reset.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "session_id"
                  ],
                  "type": "object"
                },
                "name": "reset_session"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": false,
                  "title": "Autonomous Research"
                },
                "description": "Launch VARRD's autonomous research engine to discover and test a trading edge. Give it a topic and it handles everything: generates a creative hypothesis using its concept knowledge base, loads data, charts the pattern, runs the statistical test, and gets the trade setup if an edge is found.\n\nBEST FOR: Exploring a space broadly. The autonomous engine excels at tangential idea generation \u2014 give it 'momentum on grains' and it might test wheat seasonal patterns, corn spread reversals, or soybean crush ratio momentum. It propagates from your seed idea into related concepts you might not think of. Great for running many hypotheses at scale.\n\nReturns a complete result \u2014 edge/no edge, stats, trade setup. Each call tests ONE hypothesis through the full pipeline. Call again for another idea.\n\nUse 'research' instead when YOU have a specific idea to test and want full control over each step.",
                "inputSchema": {
                  "properties": {
                    "asset_classes": {
                      "description": "Limit to specific asset classes. Default: all.",
                      "items": {
                        "enum": [
                          "crypto",
                          "futures",
                          "equities"
                        ],
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "context": {
                      "description": "Prior conversation context \u2014 recent user queries to use as research inspiration. Optional.",
                      "items": {
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "markets": {
                      "description": "Focus on specific markets (e.g. ['ES', 'NQ']). Omit for VARRD to choose.",
                      "items": {
                        "type": "string"
                      },
                      "type": "array"
                    },
                    "search_mode": {
                      "default": "focused",
                      "description": "focused = stay close to topic. explore = creative freedom. Default: focused.",
                      "enum": [
                        "focused",
                        "explore"
                      ],
                      "type": "string"
                    },
                    "test_type": {
                      "default": "event_study",
                      "description": "Type of statistical test. Default: event_study.",
                      "enum": [
                        "event_study",
                        "backtest",
                        "both"
                      ],
                      "type": "string"
                    },
                    "topic": {
                      "description": "Research topic or trading idea (e.g. 'BTC 240min short setups', 'momentum on grains', 'mean reversion after VIX spikes').",
                      "type": "string"
                    }
                  },
                  "required": [
                    "topic"
                  ],
                  "type": "object"
                },
                "name": "autonomous_research"
              },
              {
                "annotations": {
                  "destructiveHint": false,
                  "idempotentHint": false,
                  "openWorldHint": true,
                  "readOnlyHint": true,
                  "title": "Get Briefed"
                },
                "description": "Get a personalized market news briefing based on your validated edge library. Profiles your strategies, searches today's news for the instruments and setups you actually trade, and writes a concise digest connecting each headline to your specific book.\n\nEach news item includes a \u21b3 line tying it to your actual positions and edges (e.g. 'your ES momentum setups', 'your GC mean-reversion edge').\n\nRequires at least 5 strong edges in your library. Costs credits.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "get_briefed"
              }
            ]
          }
        },
        "bad_protocol_status_code": 200,
        "delete_error": null,
        "delete_status_code": 200,
        "expired_session_error": null,
        "expired_session_status_code": 404,
        "issues": [
          "missing_protocol_header",
          "bad_protocol_not_rejected"
        ],
        "last_event_id_visible": false,
        "protocol_header_present": false,
        "requested_protocol_version": "2025-03-26",
        "session_id_present": true,
        "transport": "streamable-http"
      },
      "latency_ms": 13.53,
      "status": "error"
    },
    "utility_coverage_probe": {
      "details": {
        "completions": {
          "advertised": false,
          "live_probe": "not_executed",
          "sample_target": {
            "argument_name": "idea",
            "name": "test-trading-idea",
            "type": "prompt"
          }
        },
        "initialize_capability_keys": [
          "prompts",
          "resources",
          "tools"
        ],
        "pagination": {
          "metadata_signal": false,
          "next_cursor_methods": [],
          "supported": false
        },
        "tasks": {
          "advertised": false,
          "http_status": 400,
          "probe_status": "missing"
        }
      },
      "latency_ms": 7.74,
      "status": "missing"
    }
  },
  "failures": {
    "oauth_authorization_server": {
      "reason": "no_authorization_server"
    },
    "oauth_protected_resource": {
      "error": "Expecting value: line 1 column 1 (char 0)",
      "url": "https://app.varrd.com/.well-known/oauth-protected-resource"
    },
    "openid_configuration": {
      "reason": "no_authorization_server"
    },
    "server_card": {
      "error": "Expecting value: line 1 column 1 (char 0)",
      "url": "https://app.varrd.com/.well-known/mcp/server-card.json"
    },
    "transport_compliance_probe": {
      "bad_protocol_error": null,
      "bad_protocol_headers": {
        "content-type": "application/json",
        "set-cookie": "AWSALB=hAgXPPTZC0NzGfEHuG4KAz2EjDmXxltKsLjneLeNVV0zNiF3rXSuNT1enZZRLjnb1noURq67M7fCSXUgZqjgDirW8HQsrUCFs41fL+xNV35tKBnzyZzdcsIoHL30; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/, AWSALBCORS=hAgXPPTZC0NzGfEHuG4KAz2EjDmXxltKsLjneLeNVV0zNiF3rXSuNT1enZZRLjnb1noURq67M7fCSXUgZqjgDirW8HQsrUCFs41fL+xNV35tKBnzyZzdcsIoHL30; Expires=Thu, 16 Apr 2026 07:26:54 GMT; Path=/; SameSite=None",
        "strict-transport-security": "max-age=31536000; includeSubDomains"
      },
      "bad_protocol_payload": {
        "id": 410,
        "jsonrpc": "2.0",
        "result": {
          "tools": [
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": false,
                "openWorldHint": true,
                "readOnlyHint": false,
                "title": "Research"
              },
              "description": "Talk to VARRD AI \u2014 a quant research system with 15 internal tools. Describe any trading idea in plain language, or ask for specific capabilities like the ELROND expert council, backtesting, or stop-loss optimization.\n\nMULTI-TURN: First call creates a session. Keep calling with the same session_id, following context.next_actions each time.\n  1. Your idea -> VARRD charts pattern\n  2. 'test it' -> statistical test (event study or backtest)\n  3. 'show me the trade setup' -> exact entry/stop/target prices\n\nHYPOTHESIS INTEGRITY (critical):\nVARRD tests ONE hypothesis at a time \u2014 one formula, one setup. Never combine multiple setups into one formula or ask to 'test all' \u2014 each idea must be tested as a separate hypothesis for the statistics to be valid. Say 'start a new hypothesis' between ideas to reset cleanly.\n  - ALLOWED: Test the SAME setup across multiple markets ('test this on ES, NQ, and CL') \u2014 same formula, different data.\n  - NOT ALLOWED: Test multiple DIFFERENT formulas/setups at once \u2014 each is a separate hypothesis requiring its own chart-test-result cycle.\nIf ELROND council returns 4 setups, test each one separately: chart setup 1 -> test -> results -> 'start new hypothesis' -> chart setup 2 -> etc.\n\nKEY CAPABILITIES you can ask for:\n  - 'Use the ELROND council on [market]' -> 8 expert investigators\n  - 'Optimize the stop loss and take profit' -> SL/TP grid search\n  - 'Test this on ES, NQ, and CL' -> multi-market testing\n  - 'Simulate trading this with 1.5 ATR stop' -> backtest with stops\n\nEDGE VERDICTS in context.edge_verdict after testing:\n  - STRONG EDGE: Significant vs zero AND vs market baseline\n  - MARGINAL: Significant vs zero only (beats nothing, but real signal)\n  - PINNED: Significant vs market only (flat returns but different from market)\n  - NO EDGE: Neither significant test passed\n\nTERMINAL STATES: Stop when context.has_edge is true (edge found) or false (no edge \u2014 valid result). Always read context.next_actions.",
              "inputSchema": {
                "properties": {
                  "message": {
                    "description": "Your trading idea, research question, or instruction (e.g. 'test it', 'show trade setup').",
                    "type": "string"
                  },
                  "session_id": {
                    "description": "Session ID from a previous call. Omit to start a new research session.",
                    "type": "string"
                  }
                },
                "required": [
                  "message"
                ],
                "type": "object"
              },
              "name": "research"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true,
                "title": "Scan Signals"
              },
              "description": "Scan your saved strategies against current market data to see what's firing right now. Returns exact dollar entry, stop-loss, and take-profit prices for every active signal. Not a vague directional call \u2014 exact trade levels based on the validated statistical model.",
              "inputSchema": {
                "properties": {
                  "market": {
                    "description": "Filter by market symbol (e.g. 'ES', 'SPY'). Omit to scan all.",
                    "type": "string"
                  },
                  "only_firing": {
                    "default": false,
                    "description": "If true, only return strategies that are firing right now.",
                    "type": "boolean"
                  }
                },
                "type": "object"
              },
              "name": "scan"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true,
                "title": "Search Strategies"
              },
              "description": "Search your saved hypotheses by keyword or natural language query. Returns matching strategies ranked by relevance, with key stats (win rate, Sharpe, edge status). Use this to find strategies you've already validated.",
              "inputSchema": {
                "properties": {
                  "limit": {
                    "default": 10,
                    "description": "Max results to return.",
                    "type": "integer"
                  },
                  "market": {
                    "description": "Optional market filter.",
                    "type": "string"
                  },
                  "query": {
                    "description": "Search query \u2014 keywords or natural language (e.g. 'momentum strategies', 'RSI oversold').",
                    "type": "string"
                  }
                },
                "required": [
                  "query"
                ],
                "type": "object"
              },
              "name": "search"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true,
                "title": "Get Strategy Details"
              },
              "description": "Get full detail for a specific hypothesis/strategy. Returns formula, entry/exit rules, direction, performance metrics (win rate, Sharpe, profit factor, max drawdown), version history, and trade levels. Everything an agent needs to understand and act on a strategy.",
              "inputSchema": {
                "properties": {
                  "hypothesis_id": {
                    "description": "The hypothesis ID (from search or scan results).",
                    "type": "string"
                  }
                },
                "required": [
                  "hypothesis_id"
                ],
                "type": "object"
              },
              "name": "get_hypothesis"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": true,
                "title": "Check Balance"
              },
              "description": "Check your credit balance and see available credit packs. Free \u2014 no credits consumed. Call this before heavy operations to ensure you have sufficient credits.",
              "inputSchema": {
                "properties": {},
                "type": "object"
              },
              "name": "check_balance"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": false,
                "openWorldHint": true,
                "readOnlyHint": false,
                "title": "Buy Credits"
              },
              "description": "Buy credits with USDC on Base. Two modes:\n1. Call without payment_intent_id to get a Stripe deposit address.\n2. Send USDC to that address, then call again with the payment_intent_id to confirm and receive credits.\nDefault $5. Free \u2014 no credits consumed to call this.",
              "inputSchema": {
                "properties": {
                  "amount_cents": {
                    "default": 500,
                    "description": "Amount in cents (default 500 = $5.00). Minimum $5.",
                    "type": "integer"
                  },
                  "payment_intent_id": {
                    "description": "Stripe PaymentIntent ID from a previous buy_credits call. Pass this after sending USDC to confirm payment and receive credits.",
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "name": "buy_credits"
            },
            {
              "annotations": {
                "destructiveHint": true,
                "idempotentHint": true,
                "openWorldHint": false,
                "readOnlyHint": false,
                "title": "Reset Session"
              },
              "description": "Kill a broken research session and start fresh. Use this when a session gets stuck, produces errors, or enters a bad state. Free \u2014 no credits consumed. After resetting, call research without a session_id to start a new clean session.",
              "inputSchema": {
                "properties": {
                  "session_id": {
                    "description": "The session_id to reset.",
                    "type": "string"
                  }
                },
                "required": [
                  "session_id"
                ],
                "type": "object"
              },
              "name": "reset_session"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": false,
                "openWorldHint": true,
                "readOnlyHint": false,
                "title": "Autonomous Research"
              },
              "description": "Launch VARRD's autonomous research engine to discover and test a trading edge. Give it a topic and it handles everything: generates a creative hypothesis using its concept knowledge base, loads data, charts the pattern, runs the statistical test, and gets the trade setup if an edge is found.\n\nBEST FOR: Exploring a space broadly. The autonomous engine excels at tangential idea generation \u2014 give it 'momentum on grains' and it might test wheat seasonal patterns, corn spread reversals, or soybean crush ratio momentum. It propagates from your seed idea into related concepts you might not think of. Great for running many hypotheses at scale.\n\nReturns a complete result \u2014 edge/no edge, stats, trade setup. Each call tests ONE hypothesis through the full pipeline. Call again for another idea.\n\nUse 'research' instead when YOU have a specific idea to test and want full control over each step.",
              "inputSchema": {
                "properties": {
                  "asset_classes": {
                    "description": "Limit to specific asset classes. Default: all.",
                    "items": {
                      "enum": [
                        "crypto",
                        "futures",
                        "equities"
                      ],
                      "type": "string"
                    },
                    "type": "array"
                  },
                  "context": {
                    "description": "Prior conversation context \u2014 recent user queries to use as research inspiration. Optional.",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  "markets": {
                    "description": "Focus on specific markets (e.g. ['ES', 'NQ']). Omit for VARRD to choose.",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  "search_mode": {
                    "default": "focused",
                    "description": "focused = stay close to topic. explore = creative freedom. Default: focused.",
                    "enum": [
                      "focused",
                      "explore"
                    ],
                    "type": "string"
                  },
                  "test_type": {
                    "default": "event_study",
                    "description": "Type of statistical test. Default: event_study.",
                    "enum": [
                      "event_study",
                      "backtest",
                      "both"
                    ],
                    "type": "string"
                  },
                  "topic": {
                    "description": "Research topic or trading idea (e.g. 'BTC 240min short setups', 'momentum on grains', 'mean reversion after VIX spikes').",
                    "type": "string"
                  }
                },
                "required": [
                  "topic"
                ],
                "type": "object"
              },
              "name": "autonomous_research"
            },
            {
              "annotations": {
                "destructiveHint": false,
                "idempotentHint": false,
                "openWorldHint": true,
                "readOnlyHint": true,
                "title": "Get Briefed"
              },
              "description": "Get a personalized market news briefing based on your validated edge library. Profiles your strategies, searches today's news for the instruments and setups you actually trade, and writes a concise digest connecting each headline to your specific book.\n\nEach news item includes a \u21b3 line tying it to your actual positions and edges (e.g. 'your ES momentum setups', 'your GC mean-reversion edge').\n\nRequires at least 5 strong edges in your library. Costs credits.",
              "inputSchema": {
                "properties": {},
                "type": "object"
              },
              "name": "get_briefed"
            }
          ]
        }
      },
      "bad_protocol_status_code": 200,
      "delete_error": null,
      "delete_status_code": 200,
      "expired_session_error": null,
      "expired_session_status_code": 404,
      "issues": [
        "missing_protocol_header",
        "bad_protocol_not_rejected"
      ],
      "last_event_id_visible": false,
      "protocol_header_present": false,
      "requested_protocol_version": "2025-03-26",
      "session_id_present": true,
      "transport": "streamable-http"
    }
  },
  "remote_url": "https://app.varrd.com/mcp",
  "server_card_payload": null,
  "server_identifier": "io.github.augiemazza/varrd"
}