← Back to search
com.proxylink-mcp/mcp-server

com.proxylink-mcp/mcp-server

ProxyLink MCP server for finding and booking home service professionals

Status
Healthy
Score
77.4
Transport
streamable-http
Tools
4

Production readiness

Verdict
Needs remediation
Current validation evidence shows operational or discovery gaps that should be fixed first.
Critical alerts
0
Production verdicts degrade quickly when critical alerts are active.

Evidence confidence

Confidence score
65.0
Based on 20 recent validations, 26 captured checks, and validation age of 603.0 hours.
Live checks captured
26
More direct checks increase trust in the current verdict.
Validation age
603.0h
Lower age means fresher evidence.

Recommended for

OpenAI connectors
OpenAI connectors is marked compatible with score 100.
Claude Desktop
Claude Desktop is marked compatible with score 100.
Smithery
Smithery is marked compatible with score 100.
Generic Streamable HTTP
Generic Streamable HTTP is marked compatible with score 100.

Client readiness verdicts

Ready for ChatGPT custom connector
Ready
No major blockers detected.
Confidence: medium (65.0)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initializeOK
  • tools_listOK
  • transport_compliance_probeWarning
  • step_up_auth_probeWarning
  • connector_replay_probeOK — Frozen tool snapshots must survive refresh.
  • request_association_probeMissing — Roots, sampling, and elicitation should stay request-scoped.
Ready for Claude remote MCP
Ready
No major blockers detected.
Confidence: medium (65.0)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initializeOK
  • tools_listOK
  • transport_compliance_probeWarning
Unsafe for write actions
Yes
High-risk write, exec, or destructive tools need stronger auth and confirmation semantics.
Confidence: medium (65.0)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history
Disagreements: none
  • action_safety_probeError
Snapshot churn risk
Low
No material tool-surface churn detected in the latest comparison.
Confidence: medium (65.0)
Evidence provenance
Winner: history
Supporting sources: history, live_validation
Disagreements: none
  • tool_snapshot_probeOK
  • connector_replay_probeOK

Why not ready by client

ChatGPT custom connector
Ready
Remediation checklist
  • No explicit blockers recorded.
Claude remote MCP
Ready
Remediation checklist
  • No explicit blockers recorded.
Write-safe publishing
Blocked
Remediation checklist
  • No explicit blockers recorded.

Verdict traces

Production verdict
Needs remediation
Current validation evidence shows operational or discovery gaps that should be fixed first.
Confidence: medium (65.0)
Winning source: live_validation
Triggering alerts
  • validation_stale • medium • Validation evidence is stale
Client verdict trace table
VerdictStatusChecksWinning sourceConflicts
openai_connectors Ready initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe live_validation none
claude_desktop Ready initialize, tools_list, transport_compliance_probe live_validation none
unsafe_for_write_actions Yes action_safety_probe live_validation none
snapshot_churn_risk Low tool_snapshot_probe, connector_replay_probe history none

Publishability policy profiles

ChatGPT custom connector publishability
Ready
Remote MCP, auth, transport, and tool-surface checks are in acceptable shape.
  • Search Fetch Only: No
  • Write Actions Present: Yes
  • Oauth Configured: Yes
  • Admin Refresh Required: No
  • Safe For Company Knowledge: No
  • Safe For Messages Api Remote Mcp: No
Claude remote MCP publishability
Ready
Transport, discovery, and remote-MCP assumptions are satisfied.
  • Search Fetch Only: No
  • Write Actions Present: Yes
  • Oauth Configured: Yes
  • Admin Refresh Required: No
  • Safe For Company Knowledge: No
  • Safe For Messages Api Remote Mcp: No

Compatibility fixtures

ChatGPT custom connector fixture
Passes
Live checks line up with current ChatGPT connector assumptions.
  • remote_http_endpoint: Passes
  • oauth_discovery: Passes
  • frozen_tool_snapshot_refresh: Passes
  • request_association: Passes
Anthropic remote MCP fixture
Passes
Remote MCP transport and discovery assumptions are satisfied.
  • remote_transport: Passes
  • tool_discovery: Passes
  • auth_connect: Passes
  • safe_write_review: Degraded

Authenticated validation sessions

Latest profile
remote_mcp
Authenticated session used
Public score isolation
Preview endpoint
/v1/verify
CI preview endpoint
/v1/ci/preview

Public server reputation

Validation success 7d
n/a
Validation success 30d
1.0
Mean time to recover
n/a
Breaking diffs 30d
0
Registry drift frequency 30d
0
Snapshot changes 30d
0

Incident & change feed

TimestampEventDetails
Apr 09, 2026 12:11:09 AM UTC Latest validation: healthy Score 77.4 with status healthy.

Capabilities

Use-case taxonomy
development search productivity

Security posture

Tools analyzed
4
High-risk tools
2
Destructive tools
0
Exec tools
2
Egress tools
0
Secret tools
0
Bulk-access tools
0
Risk distribution
low:1, medium:1, high:2

Tool capability & risk inventory

ToolCapabilitiesRiskFindingsNotes
lookup_company read Low none No explicit safeguard hints detected.
search_knowledge_base read write exec admin High command execution freeform input surface admin mutation No explicit safeguard hints detected.
rate_knowledge_base_answer read exec High command execution freeform input surface No explicit safeguard hints detected.
create_support_ticket read write network Medium none No explicit safeguard hints detected.

Write-action governance

Governance status
Error
Safe to publish
Auth boundary
oauth_or_auth_required
Blast radius
Medium
High-risk tools
2
Confirmation signals
none
Safeguard count
0

Status detail: 2 high-risk tool(s), 2 exec-capable tool(s) are exposed behind auth, but still risky; no safeguards or confirmation signals detected.

ToolRiskFlagsSafeguards
search_knowledge_base High command execution freeform input surface admin mutation no
rate_knowledge_base_answer High command execution freeform input surface no

Action-controls diff

Snapshot changed
no
Disabled-by-default candidates
none
Manual review candidates
none
New actions
ActionRiskFlags
No newly added actions.
Changed actions
ActionChange typesRisk
No materially changed actions.

Why this score?

Access & Protocol
35/44
Connectivity, auth, and transport expectations for common clients.
Interface Quality
39.12/56
How well the tool/resource interface communicates and behaves under automation.
Security Posture
25/36
How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.
Reliability & Trust
24/24
Operational stability, consistency, and trustworthiness over time.
Discovery & Governance
23.5/28
How well the server is documented, listed, and governed in public registries.
Adoption & Market
5/8
Adoption clues and public evidence that the server is intended for external use.

Algorithmic score breakdown

Auth Operability
4/4
Measures whether auth discovery and protected access behave predictably for clients.
Error Contract Quality
2.1/4
Grades machine-readable error structure, status alignment, and remediation hints.
Rate-Limit Semantics
2/4
Checks whether quota/throttle responses are deterministic and automation-friendly.
Schema Completeness
2/4
Completeness of tool descriptions, parameter docs, examples, and schema shape.
Backward Compatibility
4/4
Stability score across tool schema/name drift relative to prior validations.
SLO Health
4/4
Availability, latency, and burst-failure profile across recent validation history.
Security Hygiene
3/4
HTTPS posture, endpoint hygiene, and response-surface hardening checks.
Task Success
4/4
Can an agent reliably initialize, enumerate tools, and execute core MCP flows?
Trust Confidence
4/4
Confidence-adjusted reliability score that penalizes low evidence volume.
Abuse/Noise Resilience
4/4
How well the server preserves core behavior in the presence of noisy traffic patterns.
Prompt Contract
2/4
Quality of prompt metadata, argument shape, and prompt discoverability for clients.
Resource Contract
4/4
How completely resources and resource templates describe URIs, types, and usage shape.
Discovery Metadata
3/4
Homepage, docs, icon, repository, support, and license coverage for directory consumers.
Registry Consistency
2/4
Agreement between stored registry metadata, live server-card data, and current validation output.
Installability
4/4
How cleanly a real client can connect, initialize, enumerate tools, and proceed through auth.
Session Semantics
4/4
Determinism and state behavior across repeated MCP calls, including sticky-session surprises.
Tool Surface Design
3/4
Naming clarity, schema ergonomics, and parameter complexity across the tool surface.
Result Shape Stability
3/4
Stability of declared output schemas across validations, with penalties for drift or missing shapes.
OAuth Interop
3/4
Depth and client compatibility of OAuth/OIDC metadata beyond the minimal protected-resource check.
Recovery Semantics
0/4
Whether failures include actionable machine-readable next steps such as retry or upgrade guidance.
Maintenance Signal
4/4
Versioning, update recency, and historical validation cadence that indicate active stewardship.
Adoption Signal
2/4
Directory presence and distribution clues that suggest the server is intended for external use.
Freshness Confidence
4/4
Confidence that recent validations are current enough and dense enough to trust operationally.
Transport Fidelity
4/4
Whether declared transport metadata matches the observed endpoint behavior and response formats.
Spec Recency
2/4
How close the server’s claimed MCP protocol version is to the latest known public revision.
Session Resume
3/4
Whether Streamable HTTP session identifiers and resumed requests behave cleanly for real clients.
Step-Up Auth
3/4
Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.
Transport Compliance
2/4
Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.
Utility Coverage
2/4
Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.
Advanced Capability Coverage
3/4
Coverage of newer MCP surfaces like roots, sampling, elicitation, structured output, and related metadata.
Connector Publishability
3/4
How ready the server looks for client catalogs and managed connector programs.
Tool Snapshot Churn
4/4
Stability of the tool surface across recent validations, including add/remove and output-shape drift.
Connector Replay
4/4
Whether a previously published frozen connector snapshot would remain backward compatible after the latest tool refresh.
Request Association
3/4
Whether roots, sampling, and elicitation appear tied to active client requests instead of arriving unsolicited on idle sessions.
Interactive Flow Safety
3/4
Whether prompts and docs steer users toward safe auth flows instead of pasting secrets directly.
Action Safety
2/4
Risk-weighted view of destructive, exec, egress, and confirmation semantics across the tool surface.
Official Registry Presence
4/4
Whether the server appears directly or indirectly in the official MCP registry.
Provenance Divergence
4/4
How closely official registry metadata, the live server card, and public repo/package signals agree with each other.
Safety Transparency
4/4
Clarity of docs, auth disclosure, support links, and other trust signals visible to integrators.
Tool Capability Clarity
4/4
How clearly the tool surface communicates whether each action reads, writes, deletes, executes, or exports data.
Destructive Operation Safety
3/4
Penalizes delete/revoke/destroy style tools unless auth and safeguards reduce blast radius.
Egress / SSRF Resilience
3/4
Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.
Execution / Sandbox Safety
2/4
Evaluates shell, code, script, and command-execution exposure and whether that surface appears contained.
Data Exfiltration Resilience
3/4
Assesses export, dump, backup, and bulk-read behavior against the surrounding auth and safeguard signals.
Least Privilege Scope
3/4
Rewards scoped auth metadata and penalizes broad or missing scopes around privileged tools.
Secret Handling Hygiene
3/4
Assesses secret-bearing tools, token leakage risk, and whether the public surface avoids obvious secret exposure.
Supply Chain Signal
2.5/4
Public metadata signal for repository, changelog, license, versioning, and recency that supports supply-chain trust.
Input Sanitization Safety
3/4
Penalizes risky freeform string inputs when schemas do not constrain URLs, code, paths, queries, or templates.
Tool Namespace Clarity
4/4
Measures naming uniqueness and ambiguity across the tool namespace to reduce collision and confusion risk.

Compatibility profiles

OpenAI Connectors
100.0
compatible
No major blockers detected.
Connector URL: https://proxylink-mcp.com
# Complete OAuth in the client when prompted.
# Server: com.proxylink-mcp/mcp-server
Claude Desktop
100.0
compatible
No major blockers detected.
{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": ["mcp-remote", "https://proxylink-mcp.com"]
    }
  }
}
Smithery
100.0
compatible
No major blockers detected.
smithery mcp add "https://proxylink-mcp.com"
Generic Streamable HTTP
100.0
compatible
No major blockers detected.
curl -sS https://proxylink-mcp.com -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Actionable remediation

SeverityRemediationWhy it mattersRecommended action
High Add confirmation and dry-run semantics for risky actions High-risk write, delete, exec, or egress tools should communicate safeguards clearly. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
High Align session and protocol behavior with Streamable HTTP expectations Clients increasingly rely on MCP-Protocol-Version, session teardown, and expired-session semantics. Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec.
Playbook
  • Return `Mcp-Session-Id` and `Mcp-Protocol-Version` headers consistently on streamable HTTP responses.
  • Honor `DELETE` session teardown and return `404` when a deleted session is reused.
  • Reject invalid protocol-version headers with `400 Bad Request`.
High Associate roots, sampling, and elicitation with active client requests Modern MCP guidance expects roots, sampling, and elicitation traffic to be tied to an active client request instead of arriving unsolicited on idle sessions. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
High Publish a complete server card Missing or incomplete server-card metadata weakens discovery, documentation, and trust signals. Serve /.well-known/mcp/server-card.json and include tools, prompts/resources, homepage, and support links.
Playbook
  • Publish `/.well-known/mcp/server-card.json`.
  • Include homepage, repository, support, tools, prompts/resources, and auth metadata.
  • Revalidate the server after publishing the card.
Medium Adopt a current MCP protocol revision Older protocol revisions reduce compatibility with newer clients and registry programs. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Medium Close connector-publishing gaps Connector catalogs care about protocol recency, session behavior, auth clarity, and tool-surface stability. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Medium Document minimal scopes and return cleaner auth challenges Modern clients expect granular scopes and step-up auth signals such as WWW-Authenticate scope hints. Return granular scopes and WWW-Authenticate challenge hints instead of forcing overly broad auth upfront.
Playbook
  • Advertise the narrowest viable scopes in OAuth metadata.
  • Return `WWW-Authenticate` challenges with scope or insufficient-scope hints when additional consent is needed.
  • Revalidate with both public discovery and auth-required flows.
Medium Publish OpenID configuration OIDC metadata improves token validation and client compatibility. Expose /.well-known/openid-configuration with issuer, jwks_uri, and supported grants.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Medium Repair prompts/list or stop advertising prompts Prompt metadata should either work live or be removed from the advertised capability set. Only advertise prompts if prompts/list works and prompt arguments are documented.
Playbook
  • Only advertise prompts that are actually accessible.
  • Add prompt descriptions and argument docs.
  • Run a live `prompts/list` check after any prompt changes.
Medium Respond to validation evidence is stale Latest validation is 603.0 hours old. Trigger a fresh validation run or increase scheduler priority for this server.
Playbook
  • Queue a new validation run now.
  • Inspect whether the scheduler priority should be raised for this server.
  • Do not rely on stale evidence for production decisions.
Medium Support resumable HTTP sessions cleanly Modern MCP clients increasingly expect resumable session behavior on streamable HTTP transports. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.
Low Expose modern utility surfaces like completions, pagination, or tasks Utility coverage improves interoperability with larger clients and long-lived agent workflows. Expose completions, pagination, and task metadata where supported so larger clients can plan and resume work safely.
Playbook
  • Advertise `completions`, pagination cursors, and `tasks` only when they are actually supported.
  • Return `nextCursor` on large list operations when pagination is available.
  • Document task support and whether it requires step-up auth.
Low Publish newer MCP capability signals Roots, sampling, elicitation, structured outputs, and related metadata improve client understanding and ranking. Inspect the latest validation evidence and resolve the client-visible regression.
Playbook
  • Inspect the latest validation evidence.
  • Resolve the highest-severity client-facing gap first.
  • Revalidate and confirm the score and verdict improve.

Point loss breakdown

ComponentCurrentPoints missing
Recovery Semantics 0/4 -4.0
Utility Coverage 2/4 -2.0
Transport Compliance 2/4 -2.0
Spec Recency 2/4 -2.0
Schema Completeness 2/4 -2.0
Registry Consistency 2/4 -2.0
Rate Limit Semantics 2/4 -2.0
Prompt Contract 2/4 -2.0
Execution Sandbox Safety 2/4 -2.0
Adoption Signal 2/4 -2.0
Action Safety 2/4 -2.0
Error Contract 2.1/4 -1.9

Validation diff

Score delta
0
Summary changed
no
Tool delta
0
Prompt delta
0
Auth mode changed
no
Write surface expanded
no
Protocol regressed
no
Registry drift changed
no

Regressed checks: none

Improved checks: none

ComponentPreviousLatestDelta
No component deltas between the latest two runs.

Tool snapshot diff & changelog

Snapshot changed
no
Added tools
none
Removed tools
none
Required-argument changes
ToolAdded required argsRemoved required args
No required-argument changes detected.
Output-schema drift
ToolPrevious propertiesLatest properties
No output-schema drift detected.

Connector replay

Status
OK
Backward compatible
Would break after refresh
Added tools
none
Removed tools
none
Additive output changes
none
Required-argument replay breaks
ToolAdded required argsRemoved required args
No required-argument replay breaks detected.
Output-schema replay breaks
ToolRemoved propertiesAdded properties
No output-schema replay breaks detected.

Transport compliance drilldown

Probe status
Warning
Transport
streamable-http
Session header
no
Protocol header
no
Bad protocol response
400
DELETE teardown
n/a
Expired session retry
n/a
Last-Event-ID visible
no

Issues: missing_session_id, missing_protocol_header

Request association

Status
Missing
Advertised capabilities
none
Observed idle methods
none
Violating methods
none
Probe HTTP status
n/a
Issues
none

Utility coverage

Probe status
Missing
Completions
not detected
Completion probe target: { "type": "resource", "uri": "kb://usage-guide" }
Pagination
not detected
No nextCursor evidence.
Tasks
Missing
Advertised: no

Benchmark tasks

Benchmark taskStatusEvidence
Discover tools Passes
  • initializeOK
  • tools_listOK
Read-only fetch flow Passes
  • resource_readOK
  • read_only_tool_surfaceOK
OAuth-required connect Passes
  • oauth_protected_resourceOK
  • step_up_auth_probeWarning
Safe write flow with confirmation Likely to fail
  • action_safety_probeError

Registry & provenance divergence

Probe status
OK
Direct official match
yes
Drift fields
none
FieldRegistryLive server card
Titlen/an/a
Versionn/an/a
Homepagen/an/a

Active alerts

Aliases & registry graph

IdentifierSourceCanonicalScore
com.proxylink-mcp/mcp-server official_registry yes 77.36

Alias consolidation

Canonical identifier
com.proxylink-mcp/mcp-server
Duplicate aliases
0
Registry sources
official_registry
Homepages
none
Source disagreements
FieldWhat differsObserved values
No source disagreements detected.

Install snippets

Openai Connectors
Connector URL: https://proxylink-mcp.com
# Complete OAuth in the client when prompted.
# Server: com.proxylink-mcp/mcp-server
Claude Desktop
{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": ["mcp-remote", "https://proxylink-mcp.com"]
    }
  }
}
Smithery
smithery mcp add "https://proxylink-mcp.com"
Generic Http
curl -sS https://proxylink-mcp.com -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Agent access & tool surface

Live server tools
lookup_company search_knowledge_base rate_knowledge_base_answer create_support_ticket
Observed from the latest live validation against https://proxylink-mcp.com. This is the target server surface, not Verify's own inspection tools.
Live capability counts
4 tools • 0 prompts • 1 resources
Counts come from the latest tools/list, prompts/list, and resources/list checks.
Inspect with Verify
search_servers recommend_servers get_server_report compare_servers
Use Verify itself to search, recommend, compare, and fetch the full report for com.proxylink-mcp/mcp-server.
Direct machine links

Claims & monitoring

Server ownership

No verified maintainer claim recorded.

Watch subscriptions
0
Teams: none

Alert routing

Active watches
0
Generic webhooks
0
Slack routes
0
Teams routes
0
Email routes
0
WatchTeamChannelsMinimum severity
No active watch destinations.

Maintainer analytics

Validation Run Count
20
Average Latency Ms
583.4
Healthy Run Ratio Recent
1.0
Registry Presence Count
1
Active Alert Count
1
Watcher Count
0
Verified Claim
False
Taxonomy Tags
development, search, productivity
Score Trend
77.36, 77.36, 77.36, 77.36, 77.36, 77.36, 77.36, 77.36, 77.36, 77.36
Remediation Count
13
High Risk Tool Count
2
Destructive Tool Count
0
Exec Tool Count
2

Maintainer response quality

Score
16.67
Verified claim
Support contact
Changelog present
Incident notes present
Tool changes documented
Annotation history
Annotation count
0

Maintainer annotations

No maintainer annotations have been recorded yet.

Maintainer rebuttals & expected behavior

No maintainer rebuttals or expected-behavior overrides are recorded yet.

Latest validation evidence

Latest summary
Healthy
Validation profile
remote_mcp
Started
Apr 09, 2026 12:11:08 AM UTC
Latency
649.9 ms

Failures

Checks

CheckStatusLatencyEvidence
action_safety_probe Error n/a 2 high-risk, 2 exec-capable tool(s); auth present; safeguards=0; confirmation=none.
advanced_capabilities_probe Warning n/a Only 2 capability signal(s): resource links, resources.
connector_publishability_probe Warning n/a Publishability blockers: action safety, server card.
connector_replay_probe OK n/a Backward compatible with no breaking tool-surface changes.
determinism_probe OK 34.8 ms Check completed
initialize OK 88.6 ms Protocol 2025-03-26
interactive_flow_probe OK n/a Check completed
oauth_authorization_server OK 38.4 ms authorization_endpoint, code_challenge_methods_supported, grant_types_supported, issuer
oauth_protected_resource OK 52.6 ms 1 authorization server(s)
official_registry_probe OK n/a Check completed
openid_configuration Error 22.7 ms Client error '404 Not Found' for url 'https://proxylink-mcp.com/.well-known/openid-configuration' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
probe_noise_resilience OK 36.1 ms Fetched https://proxylink-mcp.com/robots.txt
prompt_get Missing n/a not advertised
prompts_list Missing 31.9 ms not supported
protocol_version_probe Warning n/a Claims 2025-03-26; 2 release(s) behind 2025-11-25.
provenance_divergence_probe OK n/a Check completed
request_association_probe Missing n/a No request-association capabilities were advertised.
resource_read OK 50.2 ms 1 resource content item(s) returned
resources_list OK 25.8 ms 1 resource item(s) exposed
server_card Error 80.9 ms Client error '404 Not Found' for url 'https://proxylink-mcp.com/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
session_resume_probe Warning n/a no session id
step_up_auth_probe Warning n/a Oauth detected.
tool_snapshot_probe OK n/a Check completed
tools_list OK 52.0 ms 4 tool(s) exposed
transport_compliance_probe Warning 26.4 ms Issues: missing session id, missing protocol header (bad protocol=400).
utility_coverage_probe Missing 30.6 ms No completions evidence; no pagination evidence; tasks missing.

Raw evidence view

Show raw JSON evidence
{
  "checks": {
    "action_safety_probe": {
      "details": {
        "auth_present": true,
        "confirmation_signals": [],
        "safeguard_count": 0,
        "summary": {
          "bulk_access_tools": 0,
          "capability_distribution": {
            "admin": 1,
            "exec": 2,
            "network": 1,
            "read": 4,
            "write": 2
          },
          "destructive_tools": 0,
          "egress_tools": 0,
          "exec_tools": 2,
          "high_risk_tools": 2,
          "risk_distribution": {
            "critical": 0,
            "high": 2,
            "low": 1,
            "medium": 1
          },
          "secret_tools": 0,
          "tool_count": 4
        }
      },
      "latency_ms": null,
      "status": "error"
    },
    "advanced_capabilities_probe": {
      "details": {
        "capabilities": {
          "completions": false,
          "elicitation": false,
          "prompts": false,
          "resource_links": true,
          "resources": true,
          "roots": false,
          "sampling": false,
          "structured_outputs": false
        },
        "enabled": [
          "resource_links",
          "resources"
        ],
        "enabled_count": 2,
        "initialize_capability_keys": [
          "resources",
          "tools"
        ]
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_publishability_probe": {
      "details": {
        "blockers": [
          "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": true
        },
        "high_risk_tools": 2,
        "tool_count": 4,
        "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": "fc71370db5fe742a85c7441c611ff0b0766ffe78164170d1c1e14094f4954e27",
        "errors": [],
        "matches": 2,
        "stable_ratio": 1.0,
        "successful": 2
      },
      "latency_ms": 34.84,
      "status": "ok"
    },
    "initialize": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "strict-transport-security": "max-age=63072000"
        },
        "http_status": 200,
        "payload": {
          "id": 1,
          "jsonrpc": "2.0",
          "result": {
            "capabilities": {
              "resources": {},
              "tools": {
                "listChanged": false
              }
            },
            "protocolVersion": "2025-03-26",
            "serverInfo": {
              "name": "proxylink-mcp",
              "version": "2.0.0"
            }
          }
        },
        "url": "https://proxylink-mcp.com"
      },
      "latency_ms": 88.56,
      "status": "ok"
    },
    "interactive_flow_probe": {
      "details": {
        "oauth_supported": true,
        "prompt_available": false,
        "risk_hits": [],
        "safe_hits": []
      },
      "latency_ms": null,
      "status": "ok"
    },
    "oauth_authorization_server": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "strict-transport-security": "max-age=63072000"
        },
        "http_status": 200,
        "payload": {
          "authorization_endpoint": "https://proxylink-mcp.com//oauth/authorize",
          "code_challenge_methods_supported": [
            "S256"
          ],
          "grant_types_supported": [
            "authorization_code",
            "refresh_token"
          ],
          "issuer": "https://proxylink-mcp.com/",
          "registration_endpoint": "https://proxylink-mcp.com//oauth/register",
          "response_types_supported": [
            "code"
          ],
          "token_endpoint": "https://proxylink-mcp.com//oauth/token"
        },
        "url": "https://proxylink-mcp.com/.well-known/oauth-authorization-server"
      },
      "latency_ms": 38.4,
      "status": "ok"
    },
    "oauth_protected_resource": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "strict-transport-security": "max-age=63072000"
        },
        "http_status": 200,
        "payload": {
          "authorization_servers": [
            "https://proxylink-mcp.com/"
          ],
          "resource_server": "https://proxylink-mcp.com/"
        },
        "url": "https://proxylink-mcp.com/.well-known/oauth-protected-resource"
      },
      "latency_ms": 52.62,
      "status": "ok"
    },
    "official_registry_probe": {
      "details": {
        "direct_match": true,
        "official_peer_count": 1,
        "registry_identifier": "com.proxylink-mcp/mcp-server",
        "registry_source": "official_registry"
      },
      "latency_ms": null,
      "status": "ok"
    },
    "openid_configuration": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://proxylink-mcp.com/.well-known/openid-configuration'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://proxylink-mcp.com/.well-known/openid-configuration"
      },
      "latency_ms": 22.72,
      "status": "error"
    },
    "probe_noise_resilience": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "strict-transport-security": "max-age=63072000"
        },
        "http_status": 404,
        "url": "https://proxylink-mcp.com/robots.txt"
      },
      "latency_ms": 36.08,
      "status": "ok"
    },
    "prompt_get": {
      "details": {
        "reason": "not_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "prompts_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "strict-transport-security": "max-age=63072000"
        },
        "http_status": 200,
        "payload": {
          "error": {
            "code": -32601,
            "message": "Unknown method: prompts/list"
          },
          "id": 3,
          "jsonrpc": "2.0"
        },
        "reason": "not_supported",
        "url": "https://proxylink-mcp.com"
      },
      "latency_ms": 31.93,
      "status": "missing"
    },
    "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": 1,
        "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": {
        "headers": {
          "content-type": "application/json",
          "strict-transport-security": "max-age=63072000"
        },
        "http_status": 200,
        "payload": {
          "id": 6,
          "jsonrpc": "2.0",
          "result": {
            "contents": [
              {
                "mimeType": "text/markdown",
                "text": "# Knowledge Base Tool Usage Guide\n\n## Overview\nThe knowledge base system allows you to search company-specific documentation, policies, procedures, and information. This guide helps you use the KB tools effectively in natural conversation.\n\n## Tool Workflow & Sequence\n\n### Standard Flow:\n1. **lookup_company** \u2192 Find the company and get their tenant_id\n2. **search_knowledge_base** \u2192 Query their knowledge base with the tenant_id\n3. **rate_knowledge_base_answer** \u2192 Collect feedback to improve answer quality\n\n## Tool Descriptions\n\n### 1. lookup_company\n**Purpose:** Find a company by name to access their knowledge base.\n\n**When to Use:**\n- Always use this FIRST before any knowledge base search\n- When the user mentions a company name\n- When switching between different companies\n\n**Parameters:**\n- `company_name` (required): The company name to look up\n\n**Example Flow:**\n```\nUser: \"What's ABC Plumbing's warranty policy?\"\nAssistant: *Calls lookup_company(\"ABC Plumbing\")*\n```\n\n**What You Get Back:**\n- Company name\n- Tenant ID (needed for searches)\n- Number of documents in their KB\n- KB status (enabled/disabled)\n\n**Important Notes:**\n- Multiple companies may match - present options to user\n- If KB is disabled or empty, inform user politely\n- Store the tenant_id for subsequent searches\n\n---\n\n### 2. search_knowledge_base\n**Purpose:** Search a company's knowledge base for specific information.\n\n**When to Use:**\n- After successfully getting a tenant_id from lookup_company\n- When user asks questions about company policies, procedures, services, etc.\n- For any information that would be in company documentation\n\n**Parameters:**\n- `tenant_id` (required): From lookup_company result\n- `query` (required): The user's question in natural language\n\n**Query Best Practices:**\n- **ALWAYS pass the user's exact question verbatim** - do not extract keywords or rephrase\n- The query parameter should be the user's original question word-for-word\n- Do NOT convert questions into keyword lists or topic phrases\n- The system handles natural language queries better than keyword extraction\n\n**Good Examples:**\n- \"How do I create an invite link so other managers can join my fantasy football league?\"\n- \"What is the warranty policy for plumbing work?\"\n- \"What are the hotel's check-in and check-out times?\"\n\n**Bad Examples (DO NOT DO THIS):**\n- \"fantasy football league commissioner invite link add teams managers join league\"\n- \"warranty policy plumbing\"\n- \"check-in check-out times hotel\"\n\n**What You Get Back:**\n- Synthesized answer (RAG-powered, from multiple sources)\n- Top 3 source documents with relevance scores\n- Query ID (for rating feedback)\n\n**Important Notes:**\n- Answers are synthesized from multiple document chunks\n- Always cite that information comes from company's knowledge base\n- If no information found, acknowledge and offer to help differently\n\n---\n\n### 3. rate_knowledge_base_answer\n**Purpose:** Collect user feedback on answer quality to improve the system.\n\n**Proactively Ask for Feedback - This helps improve the knowledge base!**\n\n**When to Use:**\n- After providing any knowledge base answer\n- When user acknowledges or responds to your answer\n- If user shows any reaction (positive or negative) to information\n- Even if user just says \"thanks\" or \"okay\"\n\n**Parameters:**\n- `query_id` (required): From search_knowledge_base response\n- `rating` (required): 1-5 integer (1=poor, 5=excellent)\n- `helpful` (required): Boolean (was the answer helpful?)\n- `comment` (optional): Additional feedback text\n\n**How to Collect Feedback:**\n\n**Active Approach - Ask Directly:**\nAfter providing an answer, prompt for feedback:\n- \"Was this information helpful for you?\"\n- \"Did that answer your question about [topic]?\"\n- \"Let me know if that information was useful!\"\n\n**Map User Responses to Ratings:**\n- User: \"Yes, that helps!\" \u2192 helpful=true, rating=4-5\n- User: \"Perfect, thanks!\" \u2192 helpful=true, rating=5\n- User: \"Not really what I was looking for\" \u2192 helpful=false, rating=2-3\n- User: \"That doesn't help\" \u2192 helpful=false, rating=1-2\n- User: \"Sort of\" or \"I guess\" \u2192 helpful=true, rating=3\n\n**Don't Wait for Explicit Feedback:**\n- If user asks a follow-up question \u2192 rate previous answer as helpful=true, rating=3-4\n- If user changes topic after answer \u2192 rate as helpful=true, rating=3\n- If user seems satisfied \u2192 collect positive rating\n- If user seems confused \u2192 collect lower rating and help further\n\n**Best Practice:** Aim to collect feedback on most answers, but keep it conversational and non-intrusive.\n\n---\n\n## Conversation Patterns\n\n### Pattern 1: Direct Company Question\n```\nUser: \"What's ProTech HVAC's service area?\"\n\nAssistant Flow:\n1. Call lookup_company(\"ProTech HVAC\")\n2. If found, call search_knowledge_base(tenant_id, \"What is the service area coverage?\")\n3. Present answer naturally: \"According to ProTech HVAC's documentation, they serve...\"\n4. Ask for feedback: \"Was this information helpful?\"\n5. Based on response, call rate_knowledge_base_answer with appropriate rating\n```\n\n### Pattern 2: Multiple Questions Same Company\n```\nUser: \"Tell me about ABC Plumbing's warranty\"\nAssistant: *lookup + search, provide answer*\n\nUser: \"What about their emergency services?\"\nAssistant: *search only (already have tenant_id), provide answer*\n```\n\n**Key:** Remember tenant_id from lookup_company for the entire conversation session about that company.\n\n### Pattern 3: Unknown Company\n```\nUser: \"What's XYZ Services' policy on refunds?\"\n\nAssistant Flow:\n1. Call lookup_company(\"XYZ Services\")\n2. If not found: \"I don't have access to XYZ Services' knowledge base. I can help you with companies that have provided their documentation. Would you like me to help with something else?\"\n```\n\n### Pattern 4: Multiple Companies Match\n```\nUser: \"What does ABC offer?\"\n\nAssistant Flow:\n1. Call lookup_company(\"ABC\")\n2. Multiple matches returned\n3. Present options: \"I found multiple companies matching 'ABC':\n   - ABC Plumbing (Tenant ID: xxx)\n   - ABC HVAC Services (Tenant ID: yyy)\n   \n   Which company would you like to know about?\"\n```\n\n---\n\n## Best Practices\n\n### DO:\n- \u2705 Always call lookup_company first (every time for a new company)\n- \u2705 Use natural language queries in search_knowledge_base\n- \u2705 Cite that information comes from company's knowledge base\n- \u2705 Present information conversationally, not robotically\n- \u2705 Acknowledge when information isn't found\n- \u2705 Store tenant_id for multiple questions about same company\n- \u2705 Include relevant context in queries for better results\n- \u2705 **Proactively ask for feedback** after providing answers\n- \u2705 Collect ratings on most knowledge base responses\n- \u2705 Use conversational prompts like \"Was this helpful?\" or \"Did that answer your question?\"\n\n### DON'T:\n- \u274c Skip lookup_company and guess tenant_id\n- \u274c Search without a valid tenant_id\n- \u274c Make up information if KB search returns nothing\n- \u274c Skip collecting feedback without a good reason\n- \u274c Say \"according to the vector search\" or technical jargon\n- \u274c Expose internal implementation details (RAG, embeddings, etc.)\n- \u274c Mention query_id explicitly (collect feedback naturally)\n\n---\n\n## Handling Edge Cases\n\n### Case: No KB Documents\n```\nResponse: \"This company hasn't set up their knowledge base yet, so I don't have access to their documentation. You may want to contact them directly for this information.\"\n```\n\n### Case: Search Returns No Results\n```\nResponse: \"I couldn't find information about [topic] in [Company]'s knowledge base. This might not be documented, or it might be phrased differently. Would you like me to search for something related?\"\n```\n\n### Case: Partial/Incomplete Answer\n```\nResponse: \"Based on [Company]'s documentation, [provide what was found]. However, I don't see complete details about [missing part]. You may want to contact them directly for more specific information.\"\n```\n\n### Case: User Asks About Multiple Companies\n```\nHandle them sequentially:\n1. Complete the query for Company A\n2. Then move to Company B (new lookup_company call)\n3. Don't try to compare across companies unless explicitly asked\n```\n\n---\n\n## Response Quality Guidelines\n\n### Good Response Example:\n```\nUser: \"What's ABC Plumbing's service area?\"\nAssistant: \"According to ABC Plumbing's documentation, they provide services throughout the greater Seattle area, including King, Pierce, and Snohomish counties. They offer both residential and commercial plumbing services in these regions.\"\n```\n\n### Bad Response Example:\n```\n\u274c \"The RAG system returned chunk relevance scores of 0.89 from document ID abc123...\"\n\u274c \"Query ID xyz789 indicates that based on vector similarity...\"\n\u274c \"I found information with the following embeddings...\"\n```\n\n**Always sound natural and hide technical implementation details.**\n\n---\n\n## Rating Collection - Proactive Approach\n\n**Default Behavior:** Actively seek feedback on answers to improve the knowledge base.\n\n### Example 1 - Positive Feedback:\n```\nUser: \"What's their refund policy?\"\nAssistant: [Provides answer] \"Did that answer your question about the refund policy?\"\n\nUser: \"Yes, perfect!\"\nAssistant: *Call rate_knowledge_base_answer(query_id, rating=5, helpful=true)*\n\"Great! Let me know if you need anything else.\"\n```\n\n### Example 2 - Negative Feedback:\n```\nUser: \"What are their hours?\"\nAssistant: [Provides answer] \"Was that the information you were looking for?\"\n\nUser: \"Not really, I wanted to know about weekend hours specifically.\"\nAssistant: *Call rate_knowledge_base_answer(query_id, rating=2, helpful=false, comment=\"User needed weekend hours specifically\")*\n\"Let me search more specifically for weekend hours...\"\n```\n\n### Example 3 - Implied Feedback:\n```\nUser: \"Tell me about their services\"\nAssistant: [Provides answer]\n\nUser: \"Thanks!\" [then asks next question]\nAssistant: *Call rate_knowledge_base_answer(query_id, rating=4, helpful=true)*\n[Proceed with next question]\n```\n\n**Goal:** Collect feedback on most answers. This data is valuable for improving the knowledge base quality. Be conversational but persistent in gathering feedback.\n\n---\n\n## Multi-Turn Conversation Memory\n\n### Remember Within Session:\n- Current company tenant_id (avoid redundant lookup_company calls)\n- Previous queries about same company\n- Context from earlier in conversation\n\n### Example:\n```\nUser: \"What's ProTech's warranty policy?\"\nAssistant: *lookup + search* [provides answer, stores tenant_id]\n\nUser: \"And what about emergency services?\"\nAssistant: *search only with stored tenant_id* [provides answer]\n\nUser: \"Do they service my area?\"\nAssistant: *search only with stored tenant_id* [provides answer]\n```\n\n**Efficiency:** One lookup_company call, multiple search_knowledge_base calls.\n\n---\n\n## Summary - Quick Reference\n\n| Step | Tool | Required For | Notes |\n|------|------|-------------|-------|\n| 1 | `lookup_company` | Every new company | Store tenant_id |\n| 2 | `search_knowledge_base` | Every query | Use stored tenant_id |\n| 3 | `rate_knowledge_base_answer` | Most answers | Ask for feedback proactively |\n\n**Golden Rule:** lookup_company \u2192 search_knowledge_base \u2192 rate_knowledge_base_answer (with feedback prompt)\n\nKeep conversations natural, cite sources appropriately, proactively collect feedback to improve the system, and focus on being helpful rather than technically impressive.\n",
                "uri": "kb://usage-guide"
              }
            ]
          }
        },
        "resource_uri": "kb://usage-guide",
        "url": "https://proxylink-mcp.com"
      },
      "latency_ms": 50.22,
      "status": "ok"
    },
    "resources_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "strict-transport-security": "max-age=63072000"
        },
        "http_status": 200,
        "payload": {
          "id": 5,
          "jsonrpc": "2.0",
          "result": {
            "resources": [
              {
                "description": "Comprehensive guide for using knowledge base tools effectively in conversation",
                "mimeType": "text/markdown",
                "name": "Knowledge Base Usage Guide",
                "uri": "kb://usage-guide"
              }
            ]
          }
        },
        "url": "https://proxylink-mcp.com"
      },
      "latency_ms": 25.78,
      "status": "ok"
    },
    "server_card": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://proxylink-mcp.com/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://proxylink-mcp.com/.well-known/mcp/server-card.json"
      },
      "latency_ms": 80.86,
      "status": "error"
    },
    "session_resume_probe": {
      "details": {
        "protocol_version": "2025-03-26",
        "reason": "no_session_id",
        "resume_expected": true,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "step_up_auth_probe": {
      "details": {
        "auth_required_checks": [],
        "broad_scopes": [],
        "challenge_headers": [],
        "minimal_scope_documented": false,
        "oauth_present": true,
        "scope_specificity_ratio": 0.0,
        "step_up_signals": [],
        "supported_scopes": []
      },
      "latency_ms": null,
      "status": "warning"
    },
    "tool_snapshot_probe": {
      "details": {
        "added": [],
        "changed_outputs": [],
        "current_tool_count": 4,
        "previous_tool_count": 4,
        "removed": [],
        "similarity": 1.0
      },
      "latency_ms": null,
      "status": "ok"
    },
    "tools_list": {
      "details": {
        "headers": {
          "content-type": "application/json",
          "strict-transport-security": "max-age=63072000"
        },
        "http_status": 200,
        "payload": {
          "id": 2,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "description": "Find a company by name to access their knowledge base. Use this first before searching a company's knowledge base to get the tenant_id.",
                "inputSchema": {
                  "properties": {
                    "company_name": {
                      "description": "The name of the company to look up (e.g., 'ABC Plumbing', 'ProTech HVAC')",
                      "type": "string"
                    }
                  },
                  "required": [
                    "company_name"
                  ],
                  "type": "object"
                },
                "name": "lookup_company"
              },
              {
                "description": "Search a company's knowledge base for policies, procedures, and documentation. First use lookup_company to get the tenant_id, then use this tool to search their knowledge base.",
                "inputSchema": {
                  "properties": {
                    "original_question": {
                      "description": "The user's original question, verbatim. Always pass this for logging purposes. Do NOT extract keywords - pass the complete question as the user asked it. Example: 'How do I create an invite link for my fantasy football league?'",
                      "type": "string"
                    },
                    "query": {
                      "description": "The search query for embedding matching. Can be keywords extracted from the user's question if you believe it improves search results.",
                      "type": "string"
                    },
                    "tenant_id": {
                      "description": "Company tenant ID from lookup_company",
                      "type": "string"
                    }
                  },
                  "required": [
                    "tenant_id",
                    "query"
                  ],
                  "type": "object"
                },
                "name": "search_knowledge_base"
              },
              {
                "description": "Provide feedback on a knowledge base answer to help improve the system. Use this after receiving an answer from search_knowledge_base to rate its quality and helpfulness.",
                "inputSchema": {
                  "properties": {
                    "comment": {
                      "description": "Optional feedback comment to provide context",
                      "type": "string"
                    },
                    "helpful": {
                      "description": "Whether the answer was helpful (true or false)",
                      "type": "boolean"
                    },
                    "query_id": {
                      "description": "Query ID from the search_knowledge_base response",
                      "type": "string"
                    },
                    "rating": {
                      "description": "Rating from 1 (poor) to 5 (excellent)",
                      "maximum": 5,
                      "minimum": 1,
                      "type": "integer"
                    }
                  },
                  "required": [
                    "query_id",
                    "rating",
                    "helpful"
                  ],
                  "type": "object"
                },
                "name": "rate_knowledge_base_answer"
              },
              {
                "description": "Submit a support ticket request (e.g., address change, service cancellation). Use lookup_company first to get the tenant_id and see available ticket types with their required fields.",
                "inputSchema": {
                  "properties": {
                    "conversation": {
                      "description": "Conversation history leading to this ticket. Only include messages that occured after the ticket request was initiated, until the ticket was created.",
                      "items": {
                        "properties": {
                          "message": {
                            "description": "The message content",
                            "type": "string"
                          },
                          "source": {
                            "description": "The source of the message, either 'user' or 'agent'",
                            "enum": [
                              "user",
                              "agent"
                            ],
                            "type": "string"
                          },
                          "timestamp": {
                            "description": "ISO 8601 timestamp of the message",
                            "type": "string"
                          }
                        },
                        "required": [
                          "timestamp",
                          "source",
                          "message"
                        ],
                        "type": "object"
                      },
                      "type": "array"
                    },
                    "fields": {
                      "description": "Key-value map of field IDs to their values based on the ticket type's form fields",
                      "type": "object"
                    },
                    "tenant_id": {
                      "description": "Company tenant ID from lookup_company",
                      "type": "string"
                    },
                    "ticket_type_id": {
                      "description": "The ticket type ID (e.g., 'change-address', 'cancel-service')",
                      "type": "string"
                    },
                    "ticket_type_name": {
                      "description": "The ticket type display name (e.g., 'Change Address', 'Cancel Service')",
                      "type": "string"
                    }
                  },
                  "required": [
                    "tenant_id",
                    "ticket_type_id",
                    "ticket_type_name",
                    "fields",
                    "conversation"
                  ],
                  "type": "object"
                },
                "name": "create_support_ticket"
              }
            ]
          }
        },
        "url": "https://proxylink-mcp.com"
      },
      "latency_ms": 52.03,
      "status": "ok"
    },
    "transport_compliance_probe": {
      "details": {
        "bad_protocol_error": null,
        "bad_protocol_headers": {
          "content-type": "text/plain; charset=utf-8",
          "strict-transport-security": "max-age=63072000"
        },
        "bad_protocol_payload": {},
        "bad_protocol_status_code": 400,
        "delete_error": null,
        "delete_status_code": null,
        "expired_session_error": null,
        "expired_session_status_code": null,
        "issues": [
          "missing_session_id",
          "missing_protocol_header"
        ],
        "last_event_id_visible": false,
        "protocol_header_present": false,
        "requested_protocol_version": "2025-03-26",
        "session_id_present": false,
        "transport": "streamable-http"
      },
      "latency_ms": 26.44,
      "status": "warning"
    },
    "utility_coverage_probe": {
      "details": {
        "completions": {
          "advertised": false,
          "live_probe": "not_executed",
          "sample_target": {
            "type": "resource",
            "uri": "kb://usage-guide"
          }
        },
        "initialize_capability_keys": [
          "resources",
          "tools"
        ],
        "pagination": {
          "metadata_signal": false,
          "next_cursor_methods": [],
          "supported": false
        },
        "tasks": {
          "advertised": false,
          "http_status": 200,
          "probe_status": "missing"
        }
      },
      "latency_ms": 30.56,
      "status": "missing"
    }
  },
  "failures": {
    "openid_configuration": {
      "error": "Client error '404 Not Found' for url 'https://proxylink-mcp.com/.well-known/openid-configuration'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://proxylink-mcp.com/.well-known/openid-configuration"
    },
    "server_card": {
      "error": "Client error '404 Not Found' for url 'https://proxylink-mcp.com/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://proxylink-mcp.com/.well-known/mcp/server-card.json"
    }
  },
  "remote_url": "https://proxylink-mcp.com",
  "server_card_payload": null,
  "server_identifier": "com.proxylink-mcp/mcp-server"
}

Known versions

Validation history

7 day score delta
+0.0
30 day score delta
+0.0
Recent healthy ratio
100%
Freshness
603.0h
TimestampStatusScoreLatencyTools
Apr 09, 2026 12:11:09 AM UTC Healthy 77.4 649.9 ms 4
Apr 08, 2026 12:09:27 AM UTC Healthy 77.4 540.9 ms 4
Apr 07, 2026 12:08:33 AM UTC Healthy 77.4 647.0 ms 4
Apr 06, 2026 12:07:46 AM UTC Healthy 77.4 858.0 ms 4
Apr 05, 2026 12:07:10 AM UTC Healthy 77.4 790.2 ms 4
Apr 04, 2026 12:07:03 AM UTC Healthy 77.4 581.7 ms 4
Apr 03, 2026 12:04:46 AM UTC Healthy 77.4 547.8 ms 4
Apr 01, 2026 11:37:36 PM UTC Healthy 77.4 587.5 ms 4

Validation timeline

ValidatedSummaryScoreProtocolAuth modeToolsHigh-risk toolsChanges
Apr 09, 2026 12:11:09 AM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Apr 08, 2026 12:09:27 AM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Apr 07, 2026 12:08:33 AM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Apr 06, 2026 12:07:46 AM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Apr 05, 2026 12:07:10 AM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Apr 04, 2026 12:07:03 AM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Apr 03, 2026 12:04:46 AM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Apr 01, 2026 11:37:36 PM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Mar 31, 2026 11:32:13 PM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Mar 30, 2026 11:24:32 PM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Mar 29, 2026 11:16:47 PM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none
Mar 28, 2026 09:07:24 PM UTC Healthy 77.4 2025-03-26 oauth_supported 4 2 none

Recent validation runs

StartedStatusSummaryLatencyChecks
Apr 09, 2026 12:11:08 AM UTC Completed Healthy 649.9 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 08, 2026 12:09:27 AM UTC Completed Healthy 540.9 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 07, 2026 12:08:33 AM UTC Completed Healthy 647.0 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 06, 2026 12:07:45 AM UTC Completed Healthy 858.0 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 05, 2026 12:07:10 AM UTC Completed Healthy 790.2 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 04, 2026 12:07:02 AM UTC Completed Healthy 581.7 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 03, 2026 12:04:46 AM UTC Completed Healthy 547.8 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 01, 2026 11:37:36 PM UTC Completed Healthy 587.5 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Mar 31, 2026 11:32:13 PM UTC Completed Healthy 481.9 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Mar 30, 2026 11:24:31 PM UTC Completed Healthy 554.9 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe