ai-incident-db
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
@pipeworx/ai-incident-db
AI Incident Database (AIID) MCP — curated database of AI-caused or AI-related real-world harms. Maintained by the Responsible AI Collaborative. No auth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1861+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
search_incidents(query?, start_date?, end_date?, limit?, offset?)— search incidentsget_incident(incident_id)— full incident with linked reportslist_recent(limit?)— most recent incidentslist_taxonomies()— taxonomies used to classify incidents (CSET-AIID, GMF, etc.)
Related MCP server: ServiceNow Incident MCP
Data source
https://incidentdatabase.ai/api/ — public REST. Underlying data also browseable at https://incidentdatabase.ai/.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"ai-incident-db": {
"url": "https://gateway.pipeworx.io/ai-incident-db/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/ai-incident-db/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1861+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/search_incidents \
-H 'Content-Type: application/json' \
-d '{"query":"facial recognition bias"}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_incidents. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Run it from npm
@pipeworx/mcp-ai-incident-db is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with npx, and it forwards every call to the same
https://gateway.pipeworx.io/ai-incident-db/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"ai-incident-db": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-ai-incident-db"]
}
}
}Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
"env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.
It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to
also list ask_pipeworx and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by
default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check
your Node version's documentation.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Ai Incident Db data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Machine-readable utilities and datasets for AI agents.
Query your app's logs, metrics and incidents from your AI assistant.
Public post-incident reports as structured cases: search by symptom, read one, list by cause.
Read Physical AI datasets, projects, fleet and quality data. Requires authorized Avala access.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables interaction with Incident.io to manage incidents, severities, and health checks via natural language. Provides endpoints for getting and creating incidents.1-
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to search, fetch, create, update, comment on, and resolve ServiceNow incidents using the caller's own bearer token, so all actions respect the token owner's ServiceNow ACLs.1-
- AlicenseAqualityCmaintenanceEnables AI clients to load, annotate, and resolve Ivanti Neurons ITSM incidents through typed MCP tools, with configurable read-only and remote HTTP modes.3MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search de-identified NASA aviation safety incident reports by keyword, date range, aircraft or flight phase, fetch a full narrative and coded fields by ACN, and list the thirty covered safety topics with their report counts and NASA update dates. Answers come from NASA's periodic Report Set PDFs parsed into a queryable store, so coverage is limited to those topics.93 npmMIT