ai.baselight/baselight
Query Baselight's public catalog of 70,000+ datasets — finance, demographics, sports, and more.
Executive verdict
Current trust snapshot
trustsnap_a43a013e858e6122Own this MCP?
Claim ownership, prove control with a GitHub, DNS, or HTTP token challenge, revalidate now, publish a badge, and configure monitoring.
POST /v1/servers/ai.baselight/baselight/revalidateBadge embed
[](https://verify.sentinelsignal.io/servers/ai.baselight/baselight)
MCP TrustOps
TrustOps turns this report into operational controls: freshness SLAs, authenticated validation, semantic benchmarks, policy exports, alert subscriptions, badges, cost/compliance metadata, and runtime routing. Fresh trusted index decisions stay separate from long-tail inventory so stale scores do not masquerade as current evidence.
/v1/routeAlert subscription types
Production readiness class
Evidence confidence
Recommended for
Client compatibility verdicts
Client compatibility only means the server shape can work with a client. Production trust decision and write-action publishing are evaluated separately so a client-compatible server can still be blocked for production.
Evidence provenance
initialize• OKtools_list• OKtransport_compliance_probe• Warningstep_up_auth_probe• Warningconnector_replay_probe• OK — Frozen tool snapshots must survive refresh.request_association_probe• Missing — Roots, sampling, and elicitation should stay request-scoped.
Evidence provenance
initialize• OKtools_list• OKtransport_compliance_probe• Warning
Evidence provenance
action_safety_probe• Warning
Evidence provenance
tool_snapshot_probe• OKconnector_replay_probe• OK
Why compatibility is limited by client
Remediation checklist
- No explicit blockers recorded.
Remediation checklist
- No explicit blockers recorded.
Remediation checklist
- No explicit blockers recorded.
Verdict traces
server_degraded• medium • Latest validation is degraded
Client verdict trace table
| Verdict | Status | Checks | Winning source | Conflicts |
|---|---|---|---|---|
openai_connectors |
Partially client-compatible | initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe | live_validation | none |
claude_desktop |
Client-compatible | initialize, tools_list, transport_compliance_probe | live_validation | none |
unsafe_for_write_actions |
Publishing allowed | action_safety_probe | live_validation | none |
snapshot_churn_risk |
Low | tool_snapshot_probe, connector_replay_probe | history | none |
Publishability policy profiles
- 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
- 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
- remote_http_endpoint: Passes
- oauth_discovery: Passes
- frozen_tool_snapshot_refresh: Passes
- request_association: Passes
- remote_transport: Passes
- tool_discovery: Passes
- auth_connect: Passes
- safe_write_review: Passes
Authenticated validation sessions
Public validation is free. Authenticated validation is paid and proves scoped behavior, write-action safeguards, and authenticated tool execution.
/v1/verify/v1/ci/previewPublic server reputation
Incident & change feed
| Timestamp | Event | Details |
|---|---|---|
| May 13, 2026 10:43:52 AM UTC | Latest validation: degraded | Score 73.6 with status degraded. |
| May 13, 2026 02:41:59 AM UTC | Score changed | Score delta -0.4 versus the previous run. |
| May 12, 2026 06:40:42 PM UTC | Score changed | Score delta +0.9 versus the previous run. |
Capabilities
- OAuth:
- DCR/CIMD:
- Prompts:
- Homepage: https://baselight.ai
- Docs: none
- Support: none
- Icon: none
- Remote endpoint: https://api.baselight.app/mcp
- Server card: none
Security posture
Tool capability & risk inventory
| Tool | Capabilities | Risk | Findings | Notes |
|---|---|---|---|---|
baselight_ping |
other | Low | none | No explicit safeguard hints detected. |
baselight_search_catalog |
read write exec admin export | High | command execution bulk data access admin mutation | No explicit safeguard hints detected. |
baselight_search_tables |
read write exec admin export | High | command execution bulk data access admin mutation | No explicit safeguard hints detected. |
baselight_get_dataset_metadata |
read write exec admin | High | command execution admin mutation | No explicit safeguard hints detected. |
baselight_get_dataset_tables |
read write exec admin export | High | command execution bulk data access freeform input surface admin mutation | Safeguards hinted in metadata. |
baselight_get_table_metadata |
read write admin | Medium | admin mutation | No explicit safeguard hints detected. |
baselight_get_user |
read write filesystem admin | Medium | filesystem mutation admin mutation | No explicit safeguard hints detected. |
baselight_sdk_query_execute |
read write exec admin | High | command execution admin mutation | No explicit safeguard hints detected. |
baselight_sdk_get_results |
read write exec export | High | command execution bulk data access | Safeguards hinted in metadata. |
Write-action governance
Status detail: 6 high-risk tool(s), 6 exec-capable tool(s); auth boundary is oauth or auth required with 2 safeguard(s) and 0 confirmation signal(s).
| Tool | Risk | Flags | Safeguards |
|---|---|---|---|
baselight_search_catalog |
High | command execution bulk data access admin mutation | no |
baselight_search_tables |
High | command execution bulk data access admin mutation | no |
baselight_get_dataset_metadata |
High | command execution admin mutation | no |
baselight_get_dataset_tables |
High | command execution bulk data access freeform input surface admin mutation | yes |
baselight_sdk_query_execute |
High | command execution admin mutation | no |
baselight_sdk_get_results |
High | command execution bulk data access | yes |
Action-controls diff
New actions
| Action | Risk | Flags |
|---|---|---|
| No newly added actions. | ||
Changed actions
| Action | Change types | Risk |
|---|---|---|
| No materially changed actions. | ||
Why this score?
Algorithmic score breakdown
Compatibility profiles
Connector URL: https://api.baselight.app/mcp # Complete OAuth in the client when prompted. # Server: ai.baselight/baselight
{
"mcpServers": {
"baselight": {
"command": "npx",
"args": ["mcp-remote", "https://api.baselight.app/mcp"]
}
}
}
smithery mcp add "https://api.baselight.app/mcp"
curl -sS https://api.baselight.app/mcp -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
| Severity | Remediation | Why it matters | Recommended 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
|
| 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
|
| 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
|
| High | Publish OAuth authorization-server metadata | Clients need authorization-server metadata to discover issuer, endpoints, and DCR support. | Publish /.well-known/oauth-authorization-server from your issuer and include registration_endpoint when supported.Playbook
|
| 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
|
| 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
|
| 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
|
| 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
|
| 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
|
| Medium | Repair resources/list or stop advertising resources | Resource metadata should either work live or be removed from the advertised capability set. | Only advertise resources if resources/list works and resources expose stable URIs/types.Playbook
|
| Medium | Respond to latest validation is degraded | The server is reachable but at least one important behavior regressed. | Resolve the regressed checks and review the latest validation diff.Playbook
|
| 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
|
| 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
|
| 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
|
Point loss breakdown
| Component | Current | Points missing |
|---|---|---|
| Recovery Semantics | 0/4 | -4.0 |
| Utility Coverage | 2/4 | -2.0 |
| Trust Confidence | 2/4 | -2.0 |
| Transport Compliance | 2/4 | -2.0 |
| Spec Recency | 2/4 | -2.0 |
| Safety Transparency | 2/4 | -2.0 |
| Resource Contract | 2/4 | -2.0 |
| Registry Consistency | 2/4 | -2.0 |
| Rate Limit Semantics | 2/4 | -2.0 |
| Prompt Contract | 2/4 | -2.0 |
| Data Exfiltration Resilience | 2/4 | -2.0 |
| Auth Operability | 2/4 | -2.0 |
Validation diff
Regressed checks: none
Improved checks: none
| Component | Previous | Latest | Delta |
|---|---|---|---|
| No component deltas between the latest two runs. | |||
Tool snapshot diff & changelog
Required-argument changes
| Tool | Added required args | Removed required args |
|---|---|---|
| No required-argument changes detected. | ||
Output-schema drift
| Tool | Previous properties | Latest properties |
|---|---|---|
| No output-schema drift detected. | ||
Connector replay
Required-argument replay breaks
| Tool | Added required args | Removed required args |
|---|---|---|
| No required-argument replay breaks detected. | ||
Output-schema replay breaks
| Tool | Removed properties | Added properties |
|---|---|---|
| No output-schema replay breaks detected. | ||
Transport compliance drilldown
Issues: missing_session_id, missing_protocol_header
Request association
Utility coverage
Benchmark tasks
| Benchmark task | Status | Evidence |
|---|---|---|
| Discover tools | Passes |
|
| Read-only fetch flow | Likely to fail |
|
| OAuth-required connect | Passes |
|
| Safe write flow with confirmation | Degraded |
|
Registry & provenance divergence
| Field | Registry | Live server card |
|---|---|---|
| Title | n/a | n/a |
| Version | n/a | n/a |
| Homepage | n/a | n/a |
Active alerts
- Latest validation is degraded (medium)
The server is reachable but at least one important behavior regressed.
Aliases & registry graph
| Identifier | Source | Canonical | Score |
|---|---|---|---|
ai.baselight/baselight |
official_registry | yes | 73.62 |
Alias consolidation
Source disagreements
| Field | What differs | Observed values |
|---|---|---|
| No source disagreements detected. | ||
Install snippets
Connector URL: https://api.baselight.app/mcp # Complete OAuth in the client when prompted. # Server: ai.baselight/baselight
{
"mcpServers": {
"baselight": {
"command": "npx",
"args": ["mcp-remote", "https://api.baselight.app/mcp"]
}
}
}
smithery mcp add "https://api.baselight.app/mcp"
curl -sS https://api.baselight.app/mcp -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
tools/list, prompts/list, and resources/list checks.ai.baselight/baselight.Claims & monitoring
No verified maintainer claim recorded.
Alert routing
| Watch | Team | Channels | Minimum severity |
|---|---|---|---|
| No active watch destinations. | |||
Maintainer analytics
Maintainer response quality
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
Failures
oauth_authorization_serverClient error '404 Not Found' for url 'http://api.baselight.app/.well-known/oauth-authorization-server' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404openid_configurationClient error '404 Not Found' for url 'http://api.baselight.app/.well-known/openid-configuration' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404server_cardClient error '404 Not Found' for url 'https://api.baselight.app/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
Checks
| Check | Status | Latency | Evidence |
|---|---|---|---|
action_safety_probe |
Warning | n/a | 6 high-risk, 6 exec-capable tool(s); auth present; safeguards=2; confirmation=none. |
advanced_capabilities_probe |
Warning | n/a | Only 1 capability signal(s): prompts. |
connector_publishability_probe |
Warning | n/a | Publishability blockers: server card. |
connector_replay_probe |
OK | n/a | Backward compatible with no breaking tool-surface changes. |
determinism_probe |
OK | 29.5 ms | Check completed |
initialize |
OK | 9.2 ms | Protocol 2025-03-26 |
interactive_flow_probe |
OK | n/a | Check completed |
oauth_authorization_server |
Error | 5.1 ms | Client error '404 Not Found' for url 'http://api.baselight.app/.well-known/oauth-authorization-server' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404 |
oauth_protected_resource |
OK | 44.2 ms | 1 authorization server(s) |
official_registry_probe |
OK | n/a | Check completed |
openid_configuration |
Error | 4.8 ms | Client error '404 Not Found' for url 'http://api.baselight.app/.well-known/openid-configuration' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404 |
probe_noise_resilience |
OK | 44.4 ms | Fetched https://api.baselight.app/robots.txt |
prompt_get |
OK | 49.5 ms | 1 prompt message(s) returned |
prompts_list |
OK | 48.4 ms | 1 prompt(s) exposed |
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 |
Missing | n/a | not advertised |
resources_list |
Missing | 50.4 ms | not supported |
server_card |
Error | 200.4 ms | Client error '404 Not Found' for url 'https://api.baselight.app/.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 | 49.8 ms | 9 tool(s) exposed |
transport_compliance_probe |
Warning | 49.3 ms | Issues: missing session id, missing protocol header (bad protocol=400). |
utility_coverage_probe |
Missing | 8.3 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": 2,
"summary": {
"bulk_access_tools": 4,
"capability_distribution": {
"admin": 7,
"exec": 6,
"export": 4,
"filesystem": 1,
"other": 1,
"read": 8,
"write": 8
},
"destructive_tools": 0,
"egress_tools": 0,
"exec_tools": 6,
"high_risk_tools": 6,
"risk_distribution": {
"critical": 0,
"high": 6,
"low": 1,
"medium": 2
},
"secret_tools": 0,
"tool_count": 9
}
},
"latency_ms": null,
"status": "warning"
},
"advanced_capabilities_probe": {
"details": {
"capabilities": {
"completions": false,
"elicitation": false,
"prompts": true,
"resource_links": false,
"resources": false,
"roots": false,
"sampling": false,
"structured_outputs": false
},
"enabled": [
"prompts"
],
"enabled_count": 1,
"initialize_capability_keys": [
"prompts",
"tools"
]
},
"latency_ms": null,
"status": "warning"
},
"connector_publishability_probe": {
"details": {
"blockers": [
"server_card"
],
"criteria": {
"action_safety": true,
"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": 6,
"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": "5c780cf7f517e4f585eca9679c5a0c43e21cc7b79a18ce79778056b4f73b1c15",
"errors": [],
"matches": 2,
"stable_ratio": 1.0,
"successful": 2
},
"latency_ms": 29.5,
"status": "ok"
},
"initialize": {
"details": {
"headers": {
"content-type": "text/event-stream"
},
"http_status": 200,
"payload": {
"id": 1,
"jsonrpc": "2.0",
"result": {
"capabilities": {
"prompts": {
"listChanged": true
},
"tools": {
"listChanged": true
}
},
"protocolVersion": "2025-03-26",
"serverInfo": {
"name": "baselight-mcp-server",
"version": "1.0.0"
}
}
},
"url": "https://api.baselight.app/mcp"
},
"latency_ms": 9.17,
"status": "ok"
},
"interactive_flow_probe": {
"details": {
"oauth_supported": true,
"prompt_available": true,
"risk_hits": [],
"safe_hits": []
},
"latency_ms": null,
"status": "ok"
},
"oauth_authorization_server": {
"details": {
"error": "Client error '404 Not Found' for url 'http://api.baselight.app/.well-known/oauth-authorization-server'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "http://api.baselight.app/.well-known/oauth-authorization-server"
},
"latency_ms": 5.07,
"status": "error"
},
"oauth_protected_resource": {
"details": {
"headers": {
"content-type": "application/json; charset=utf-8",
"x-ratelimit-limit": "30",
"x-ratelimit-remaining": "29",
"x-ratelimit-reset": "60"
},
"http_status": 200,
"payload": {
"authorization_servers": [
"http://api.baselight.app"
],
"bearer_methods_supported": [
"header"
],
"resource": "http://api.baselight.app",
"resource_documentation": "http://api.baselight.app/docs",
"resource_signing_alg_values_supported": [
"RS256"
],
"scopes_supported": [
"api:mcp"
]
},
"url": "https://api.baselight.app/.well-known/oauth-protected-resource"
},
"latency_ms": 44.2,
"status": "ok"
},
"official_registry_probe": {
"details": {
"direct_match": true,
"official_peer_count": 1,
"registry_identifier": "ai.baselight/baselight",
"registry_source": "official_registry"
},
"latency_ms": null,
"status": "ok"
},
"openid_configuration": {
"details": {
"error": "Client error '404 Not Found' for url 'http://api.baselight.app/.well-known/openid-configuration'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "http://api.baselight.app/.well-known/openid-configuration"
},
"latency_ms": 4.84,
"status": "error"
},
"probe_noise_resilience": {
"details": {
"headers": {
"content-type": "application/json; charset=utf-8"
},
"http_status": 404,
"url": "https://api.baselight.app/robots.txt"
},
"latency_ms": 44.41,
"status": "ok"
},
"prompt_get": {
"details": {
"headers": {
"content-type": "text/event-stream"
},
"http_status": 200,
"payload": {
"id": 4,
"jsonrpc": "2.0",
"result": {
"description": "Initial prompt for interacting with Baselight catalog",
"messages": [
{
"content": {
"text": "You are a Baselight assistant for dataset exploration and DuckDB SQL analysis.\n\n<mcp>\nAvailable Tools:\n- \"baselight_ping\": Simple ping test to verify MCP server is responding\n- \"catalog-search\": Search the catalog for datasets using a text query and filters. Datasets in Baselight have the following format: @username.dataset. Datasets can be public or private \u2014 you can search and use all public datasets as well as the user's private datasets. This is typically the first step in the discovery workflow. (key params: query, category, limit)\n- \"catalog-table-search\": Search for tables using a text query and filters. Tables in Baselight have the following format: @username.dataset.table. Tables are grouped into datasets which can be public or private \u2014 you can search and use all public datasets as well as the user's private datasets. Search for tables directly when you are unable to find relevant datasets. (key params: query, category, limit)\n- \"catalog-dataset-inspect\": Retrieve detailed schema and metadata for a specific dataset using Baselight format @username.dataset. Use this after discovering datasets to understand their structure before querying. Tables within datasets follow the format @username.dataset.table (always double-quoted identifiers in SQL). (key params: id)\n- \"catalog-dataset-tables\": Retrieve a paginated list of tables from a specific dataset using Baselight format @username.dataset. Use this tool to browse datasets with many tables or to search for specific tables within a dataset. Each page returns up to 100 tables with metadata. (key params: id, query, page)\n- \"catalog-table-inspect\": Retrieve detailed schema and metadata for a specific table using Baselight format @username.dataset.table. Use this to understand table structure, column types, and constraints before writing SQL queries. Tables must be referenced in SQL with double quotes. (key params: id)\n- \"catalog-user-inspect\": Retrieve detailed information about a Baselight user including their profile bio, website, and public datasets. Use this to understand who owns datasets you're interested in. (key params: username)\n- \"sdk-query-execute\": Execute a SQL query on Baselight and wait for results (up to 1 minute). The query executes and returns the first 100 rows upon completion, or info about a pending query that needs more time. Use DuckDB syntax only, table format \"@username.dataset.table\" (double-quoted), SELECT queries only (no DDL/DML), no semicolon terminators, use LIMIT not TOP. If query is still PENDING, use `sdk-get-results` to continue polling. If totalResults > returned rows, use `sdk-get-results` with offset to paginate. (key params: sql)\n- \"sdk-query-get-results\": Retrieve results from a previously executed SDK job using the resultId from `sdk-query-execute`. If the query is complete, returns results immediately. If still pending, polls for up to 1 more minute. Use this after `sdk-query-execute` returns PENDING status. (key params: jobId, limit, offset)\n</mcp>\nThe current user's username is \"blt-agent\".\nCore Workflow: Search \u2192 Metadata \u2192 Execute \u2192 Status",
"type": "text"
},
"role": "user"
}
]
}
},
"prompt_name": "baselight-initial-prompt",
"url": "https://api.baselight.app/mcp"
},
"latency_ms": 49.45,
"status": "ok"
},
"prompts_list": {
"details": {
"headers": {
"content-type": "text/event-stream"
},
"http_status": 200,
"payload": {
"id": 3,
"jsonrpc": "2.0",
"result": {
"prompts": [
{
"description": "A prompt to initialize interaction with the Baselight catalog and understand its capabilities",
"name": "baselight-initial-prompt"
}
]
}
},
"url": "https://api.baselight.app/mcp"
},
"latency_ms": 48.36,
"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": {
"reason": "not_advertised"
},
"latency_ms": null,
"status": "missing"
},
"resources_list": {
"details": {
"headers": {
"content-type": "text/event-stream"
},
"http_status": 200,
"payload": {
"error": {
"code": -32601,
"message": "Method not found"
},
"id": 5,
"jsonrpc": "2.0"
},
"reason": "not_supported",
"url": "https://api.baselight.app/mcp"
},
"latency_ms": 50.42,
"status": "missing"
},
"server_card": {
"details": {
"error": "Client error '404 Not Found' for url 'https://api.baselight.app/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "https://api.baselight.app/.well-known/mcp/server-card.json"
},
"latency_ms": 200.44,
"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": 9,
"previous_tool_count": 9,
"removed": [],
"similarity": 1.0
},
"latency_ms": null,
"status": "ok"
},
"tools_list": {
"details": {
"headers": {
"content-type": "text/event-stream"
},
"http_status": 200,
"payload": {
"id": 2,
"jsonrpc": "2.0",
"result": {
"tools": [
{
"annotations": {
"openWorldHint": false,
"readOnlyHint": true
},
"description": "Simple ping test to verify MCP server is responding",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"type": "object"
},
"name": "baselight_ping",
"title": "Ping Test"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Search the catalog for datasets using a text query and filters. Datasets in Baselight have the following format: @username.dataset. Datasets can be public or private \u2014 you can search and use all public datasets as well as the user's private datasets. This is typically the first step in the discovery workflow.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"category": {
"description": "The dataset category to filter by",
"items": {
"enum": [
"Academic Research",
"Astronomy and Space Sciences",
"Crypto and Blockchain",
"Demographics and Population Studies",
"Ecommerce and Consumer Trends",
"Environmental and Climate Sciences",
"Finance and Economics",
"Healthcare",
"Media and Entertainment",
"Politics and Governance",
"Prediction Markets",
"Sports",
"Technology and IT",
"Transportation and Logistics"
],
"type": "string"
},
"type": "array"
},
"limit": {
"default": 10,
"description": "Maximum number of datasets to return (1-20, default 10)",
"maximum": 20,
"minimum": 1,
"type": "number"
},
"query": {
"description": "The search query string, used for semantic search",
"maxLength": 100,
"minLength": 1,
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "baselight_search_catalog",
"title": "search_catalog"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Search for tables using a text query and filters. Tables in Baselight have the following format: @username.dataset.table. Tables are grouped into datasets which can be public or private \u2014 you can search and use all public datasets as well as the user's private datasets. Search for tables directly when you are unable to find relevant datasets.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"category": {
"description": "The dataset category to filter by",
"items": {
"enum": [
"Academic Research",
"Astronomy and Space Sciences",
"Crypto and Blockchain",
"Demographics and Population Studies",
"Ecommerce and Consumer Trends",
"Environmental and Climate Sciences",
"Finance and Economics",
"Healthcare",
"Media and Entertainment",
"Politics and Governance",
"Prediction Markets",
"Sports",
"Technology and IT",
"Transportation and Logistics"
],
"type": "string"
},
"type": "array"
},
"limit": {
"default": 10,
"description": "Maximum number of tables to return (1-20, default 10)",
"maximum": 20,
"minimum": 1,
"type": "number"
},
"query": {
"description": "The search query string, used for semantic search",
"maxLength": 200,
"minLength": 1,
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "baselight_search_tables",
"title": "search_tables"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Retrieve detailed schema and metadata for a specific dataset using Baselight format @username.dataset. Use this after discovering datasets to understand their structure before querying. Tables within datasets follow the format @username.dataset.table (always double-quoted identifiers in SQL).",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"id": {
"description": "The identifier of the dataset to inspect, should be something like @user.dataset",
"minLength": 1,
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "baselight_get_dataset_metadata",
"title": "get_dataset_metadata"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Retrieve a paginated list of tables from a specific dataset using Baselight format @username.dataset. Use this tool to browse datasets with many tables or to search for specific tables within a dataset. Each page returns up to 100 tables with metadata.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"id": {
"description": "The identifier of the dataset to browse, should be something like @user.dataset",
"minLength": 1,
"type": "string"
},
"page": {
"default": 1,
"description": "Page number to retrieve (starts at 1). Each page contains up to 100 tables.",
"minimum": 1,
"type": "number"
},
"query": {
"default": "",
"description": "Optional text search query to filter tables by name or title. If omitted, returns all tables.",
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "baselight_get_dataset_tables",
"title": "get_dataset_tables"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Retrieve detailed schema and metadata for a specific table using Baselight format @username.dataset.table. Use this to understand table structure, column types, and constraints before writing SQL queries. Tables must be referenced in SQL with double quotes.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"id": {
"description": "The full identifier of the table to inspect, should be something like @user.dataset.table",
"minLength": 1,
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "baselight_get_table_metadata",
"title": "get_table_metadata"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Retrieve detailed information about a Baselight user including their profile bio, website, and public datasets. Use this to understand who owns datasets you're interested in.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"username": {
"description": "The username of the user to inspect",
"minLength": 1,
"type": "string"
}
},
"required": [
"username"
],
"type": "object"
},
"name": "baselight_get_user",
"title": "get_user"
},
{
"annotations": {
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": true,
"readOnlyHint": false
},
"description": "Execute a SQL query on Baselight and wait for results (up to 1 minute). The query executes and returns the first 100 rows upon completion, or info about a pending query that needs more time. Use DuckDB syntax only, table format \"@username.dataset.table\" (double-quoted), SELECT queries only (no DDL/DML), no semicolon terminators, use LIMIT not TOP. If query is still PENDING, use `sdk-get-results` to continue polling. If totalResults > returned rows, use `sdk-get-results` with offset to paginate.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"sql": {
"description": "The SQL query to execute. table identifiers should be wrapped in double quotes, like \"@user.dataset.table\". Only SELECT queries are allowed.",
"type": "string"
}
},
"required": [
"sql"
],
"type": "object"
},
"name": "baselight_sdk_query_execute",
"title": "sdk_query_execute"
},
{
"annotations": {
"openWorldHint": true,
"readOnlyHint": true
},
"description": "Retrieve results from a previously executed SDK job using the resultId from `sdk-query-execute`. If the query is complete, returns results immediately. If still pending, polls for up to 1 more minute. Use this after `sdk-query-execute` returns PENDING status.",
"execution": {
"taskSupport": "forbidden"
},
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"jobId": {
"description": "The result ID of the executed query (from `sdk-query-execute`).",
"type": "string"
},
"limit": {
"default": 100,
"description": "Number of rows to return per page (max 100). Default is 100.",
"maximum": 100,
"minimum": 1,
"type": "number"
},
"offset": {
"default": 0,
"description": "Row offset for pagination. Use to fetch subsequent pages (e.g., offset=100 for page 2).",
"minimum": 0,
"type": "number"
}
},
"required": [
"jobId"
],
"type": "object"
},
"name": "baselight_sdk_get_results",
"title": "sdk_get_results"
}
]
}
},
"url": "https://api.baselight.app/mcp"
},
"latency_ms": 49.78,
"status": "ok"
},
"transport_compliance_probe": {
"details": {
"bad_protocol_error": null,
"bad_protocol_headers": {
"content-type": "application/json"
},
"bad_protocol_payload": {
"error": {
"code": -32000,
"message": "Bad Request: Unsupported protocol version: 1999-99-99 (supported versions: 2025-11-25, 2025-06-18, 2025-03-26, 2024-11-05, 2024-10-07)"
},
"id": null,
"jsonrpc": "2.0"
},
"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": 49.29,
"status": "warning"
},
"utility_coverage_probe": {
"details": {
"completions": {
"advertised": false,
"live_probe": "not_executed",
"sample_target": null
},
"initialize_capability_keys": [
"prompts",
"tools"
],
"pagination": {
"metadata_signal": false,
"next_cursor_methods": [],
"supported": false
},
"tasks": {
"advertised": false,
"http_status": 200,
"probe_status": "missing"
}
},
"latency_ms": 8.28,
"status": "missing"
}
},
"failures": {
"oauth_authorization_server": {
"error": "Client error '404 Not Found' for url 'http://api.baselight.app/.well-known/oauth-authorization-server'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "http://api.baselight.app/.well-known/oauth-authorization-server"
},
"openid_configuration": {
"error": "Client error '404 Not Found' for url 'http://api.baselight.app/.well-known/openid-configuration'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "http://api.baselight.app/.well-known/openid-configuration"
},
"server_card": {
"error": "Client error '404 Not Found' for url 'https://api.baselight.app/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
"url": "https://api.baselight.app/.well-known/mcp/server-card.json"
}
},
"remote_url": "https://api.baselight.app/mcp",
"server_card_payload": null,
"server_identifier": "ai.baselight/baselight"
}
Known versions
1.0.0
Validation history
| Timestamp | Status | Score | Latency | Tools |
|---|---|---|---|---|
| May 13, 2026 10:43:52 AM UTC | Degraded | 73.6 | 635.2 ms | 9 |
| May 13, 2026 02:41:59 AM UTC | Degraded | 73.6 | 546.0 ms | 9 |
| May 12, 2026 06:40:42 PM UTC | Degraded | 74.0 | 627.6 ms | 9 |
| May 12, 2026 10:25:35 AM UTC | Degraded | 73.1 | 494.5 ms | 9 |
| May 12, 2026 02:24:20 AM UTC | Degraded | 69.7 | 604.4 ms | 9 |
Validation timeline
| Validated | Summary | Score | Protocol | Auth mode | Tools | High-risk tools | Changes |
|---|---|---|---|---|---|---|---|
| May 13, 2026 10:43:52 AM UTC | Degraded | 73.6 | 2025-03-26 | oauth_supported | 9 | 6 | none |
| May 13, 2026 02:41:59 AM UTC | Degraded | 73.6 | 2025-03-26 | oauth_supported | 9 | 6 | none |
| May 12, 2026 06:40:42 PM UTC | Degraded | 74.0 | 2025-03-26 | oauth_supported | 9 | 6 | none |
| May 12, 2026 10:25:35 AM UTC | Degraded | 73.1 | 2025-03-26 | oauth_supported | 9 | 6 | none |
| May 12, 2026 02:24:20 AM UTC | Degraded | 69.7 | 2025-03-26 | oauth_supported | 9 | 6 | none |
Recent validation runs
| Started | Status | Summary | Latency | Checks |
|---|---|---|---|---|
| May 13, 2026 10:43:51 AM UTC | Completed | Degraded | 635.2 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 |
| May 13, 2026 02:41:58 AM UTC | Completed | Degraded | 546.0 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 |
| May 12, 2026 06:40:41 PM UTC | Completed | Degraded | 627.6 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 |
| May 12, 2026 10:25:34 AM UTC | Completed | Degraded | 494.5 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 |
| May 12, 2026 02:24:19 AM UTC | Completed | Degraded | 604.4 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 |