Skip to main content
Glama
mcp-uk-food-hygiene

mcp-uk-food-hygiene

by pipeworx-io

mcp-uk-food-hygiene

UK Food Hygiene MCP — Food Standards Agency food hygiene ratings (FHRS) via api.ratings.food.gov.uk (keyless, official FSA open data).

Part of Pipeworx — an MCP gateway connecting AI agents to 1857+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

Tool

Description

uk_food_hygiene_search

Search UK restaurant food hygiene ratings from the Food Standards Agency FHRS — answers "is this restaurant clean", "is this takeaway safe to eat at", "food hygiene rating of X". Search by business name and/or address (a town, street, or postcode works), or by latitude/longitude + radius_miles for hygiene ratings near a point. Filter by business_type (restaurant, takeaway, pub, hotel, supermarket, mobile caterer...) and min_rating (1-5). Returns rating (0-5 in England/Wales/NI; Scotland uses "Pass"/"Improvement Required" under FHIS), inspection date, address, and inspection sub-scores. Example: uk_food_hygiene_search({ name: "Nandos", address: "Leeds" })

uk_food_hygiene_details

Get the full Food Standards Agency FHRS inspection record for one UK establishment by its FHRSID (from uk_food_hygiene_search) — rating, inspection date, sub-scores for hygiene / structural compliance / confidence in management (0 = best, higher = worse), full address, local authority contact, and geocode. Use to check how clean or safe a specific UK restaurant, takeaway, cafe, or pub is. Example: uk_food_hygiene_details({ fhrsid: 537122 })

Related MCP server: mcp-gov-uk-content

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "uk-food-hygiene": {
      "url": "https://gateway.pipeworx.io/uk-food-hygiene/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/uk-food-hygiene/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 1857+ 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/uk_food_hygiene_search \
  -H 'Content-Type: application/json' \
  -d '{"name":"Nandos","address":"Leeds"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/uk_food_hygiene_search. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-uk-food-hygiene 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/uk-food-hygiene/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "uk-food-hygiene": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-uk-food-hygiene"]
    }
  }
}

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 Uk Food Hygiene data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables querying and searching GOV.UK content through the Pipeworx MCP gateway, integrating with 673+ data sources for AI agent access.
    444 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to query Finnish Patent and Registration Office (PRH) open data via YTJ, using natural language through the Pipeworx gateway.
    206 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables natural language queries about UK Health Security Agency (UKHSA) data through the Pipeworx MCP gateway, with no API key required.
    190 npm
    MIT