Loading…
Query FDA data on drugs, food, devices, and recalls via openFDA. STDIO or Streamable HTTP.
io.github.cyanheads/openfda-mcp-server is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 78/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding io.github.cyanheads/openfda-mcp-server to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
mcp add io.github.cyanheads/openfda-mcp-server https://openfda.caseyjhand.com/mcpReview the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-26T19:35:32.496788Z",
"publishedAt": "2026-10-26T19:35:32.496788Z",
"statusChangedAt": "2026-10-26T19:35:32.496788Z"
}
},
"server": {
"name": "io.github.cyanheads/openfda-mcp-server",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://openfda.caseyjhand.com/mcp",
"type": "streamable-http"
}
],
"version": "0.9.1",
"packages": [
{
"version": "0.9.1",
"transport": {
"type": "stdio"
},
"identifier": "@cyanheads/openfda-mcp-server",
"runtimeHint": "npx",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"environmentVariables": [
{
"name": "OPENFDA_API_KEY",
"format": "string",
"description": "Free API key from open.fda.gov — increases daily limit from 1K to 120K requests."
},
{
"name": "CANVAS_PROVIDER_TYPE",
"format": "string",
"default": "duckdb",
"description": "DataCanvas staging, on by default: stage=true or a canvas_id on an openfda_search_* tool or openfda_lookup_ndc stages the matched records as a SQL table for the openfda_dataframe_* tools. The DuckDB binding ships with the server. Set to 'none' to disable."
},
{
"name": "OPENFDA_DATAFRAME_DROP_ENABLED",
"format": "string",
"default": "false",
"description": "Enable openfda_dataframe_drop, which deletes a table staged on a DataCanvas. Off by default; applies only when DataCanvas is enabled (CANVAS_PROVIDER_TYPE=duckdb)."
},
{
"name": "OPENFDA_MIRROR_ENABLED",
"format": "string",
"default": "false",
"description": "Serve exact-key lookups for drug/label, drug/ndc, drug/enforcement, and drug/drugsfda from a local bulk mirror instead of the API. Off by default; the initial harvest runs out-of-band via the mirror:init script."
},
{
"name": "OPENFDA_MIRROR_PATH",
"format": "string",
"default": "./data/openfda-mirror",
"description": "Directory holding one SQLite file per mirrored dataset."
},
{
"name": "OPENFDA_MIRROR_REFRESH_CRON",
"format": "string",
"description": "Cron expression for the in-process mirror refresh. HTTP transport only; stdio operators run mirror:refresh from the host. Requires the optional node-cron peer dependency."
},
{
"name": "OPENFDA_MIRROR_FALLBACK_LIVE",
"format": "string",
"default": "true",
"description": "Fall back to the live API when the mirror is cold, missing the record, or failing. Disable to fail loudly instead."
},
{
"name": "OPENFDA_MIRROR_REFRESH_TIMEOUT_MS",
"format": "string",
"default": "21600000",
"description": "Wall-clock budget for one scheduled refresh before it is aborted. Raise it for drug/label, the only multi-partition dataset."
},
{
"name": "OPENFDA_MIRROR_BASE_URL",
"format": "string",
"default": "https://api.fda.gov",
"description": "Host serving the openFDA bulk download manifest. Override only to harvest from a private mirror of the dumps."
},
{
"name": "MCP_LOG_LEVEL",
"format": "string",
"default": "info",
"description": "Sets the minimum log level for output (e.g., 'debug', 'info', 'warn')."
}
]
},
{
"version": "0.9.1",
"transport": {
"url": "http://localhost:3010/mcp",
"type": "streamable-http"
},
"identifier": "@cyanheads/openfda-mcp-server",
"runtimeHint": "npx",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"environmentVariables": [
{
"name": "OPENFDA_API_KEY",
"format": "string",
"description": "Free API key from open.fda.gov — increases daily limit from 1K to 120K requests."
},
{
"name": "MCP_TRANSPORT_TYPE",
"value": "http",
"format": "string",
"description": "Selects the HTTP transport."
},
{
"name": "MCP_HTTP_HOST",
"format": "string",
"default": "127.0.0.1",
"description": "The hostname for the HTTP server."
},
{
"name": "MCP_HTTP_PORT",
"format": "string",
"default": "3010",
"description": "The port to run the HTTP server on."
},
{
"name": "MCP_HTTP_ENDPOINT_PATH",
"format": "string",
"default": "/mcp",
"description": "The endpoint path for the MCP server."
},
{
"name": "MCP_AUTH_MODE",
"format": "string",
"default": "none",
"description": "Authentication mode to use: 'none', 'jwt', or 'oauth'."
},
{
"name": "CANVAS_PROVIDER_TYPE",
"format": "string",
"default": "duckdb",
"description": "DataCanvas staging, on by default: stage=true or a canvas_id on an openfda_search_* tool or openfda_lookup_ndc stages the matched records as a SQL table for the openfda_dataframe_* tools. The DuckDB binding ships with the server. Set to 'none' to disable."
},
{
"name": "OPENFDA_DATAFRAME_DROP_ENABLED",
"format": "string",
"default": "false",
"description": "Enable openfda_dataframe_drop, which deletes a table staged on a DataCanvas. Off by default; applies only when DataCanvas is enabled (CANVAS_PROVIDER_TYPE=duckdb)."
},
{
"name": "OPENFDA_MIRROR_ENABLED",
"format": "string",
"default": "false",
"description": "Serve exact-key lookups for drug/label, drug/ndc, drug/enforcement, and drug/drugsfda from a local bulk mirror instead of the API. Off by default; the initial harvest runs out-of-band via the mirror:init script."
},
{
"name": "OPENFDA_MIRROR_PATH",
"format": "string",
"default": "./data/openfda-mirror",
"description": "Directory holding one SQLite file per mirrored dataset."
},
{
"name": "OPENFDA_MIRROR_REFRESH_CRON",
"format": "string",
"description": "Cron expression for the in-process mirror refresh. HTTP transport only; stdio operators run mirror:refresh from the host. Requires the optional node-cron peer dependency."
},
{
"name": "OPENFDA_MIRROR_FALLBACK_LIVE",
"format": "string",
"default": "true",
"description": "Fall back to the live API when the mirror is cold, missing the record, or failing. Disable to fail loudly instead."
},
{
"name": "OPENFDA_MIRROR_REFRESH_TIMEOUT_MS",
"format": "string",
"default": "21600000",
"description": "Wall-clock budget for one scheduled refresh before it is aborted. Raise it for drug/label, the only multi-partition dataset."
},
{
"name": "OPENFDA_MIRROR_BASE_URL",
"format": "string",
"default": "https://api.fda.gov",
"description": "Host serving the openFDA bulk download manifest. Override only to harvest from a private mirror of the dumps."
},
{
"name": "MCP_LOG_LEVEL",
"format": "string",
"default": "info",
"description": "Sets the minimum log level for output (e.g., 'debug', 'info', 'warn')."
}
]
}
],
"repository": {
"url": "https://github.com/cyanheads/openfda-mcp-server",
"source": "github"
},
"description": "Query FDA data on drugs, food, devices, and recalls via openFDA. STDIO or Streamable HTTP."
}
}