Uk Charity Commission

@pipeworx/uk-charity-commission

The UK Register of Charities from the Charity Commission for England and Wales — a registered charity's status, objects, areas of operation, reported income and expenditure year by year, and its named trustees.

Part of Pipeworx — an MCP gateway connecting AI agents to 1684+ live data sources.

Tools

• ukcharity_search(query, limit?, registered_only?, _apiKey) — find charities by name.
• ukcharity_details(charity_number, subsidiary_number?, _apiKey) — the full register entry.
• ukcharity_financials(charity_number, subsidiary_number?, _apiKey) — filed income/expenditure history.
• ukcharity_trustees(charity_number, subsidiary_number?, _apiKey) — the trustee board.

Auth

BYO key, with PLATFORM_CHARITY_COMMISSION_KEY as the platform fallback once one is provisioned. Until then the pack is byoExpected in workers/gateway/src/pack-manifest.json and every call needs a caller-supplied _apiKey; the refusal says so in those words.

Registration is free but not instant-self-serve in one step: sign up at https://api-portal.charitycommission.gov.uk/, then subscribe to the "Charity Commission Register of Charities" product to be issued an Ocp-Apim-Subscription-Key. There is no keyless or demo path — every operation answers 401 Access Denied without the header.

Data sources

• https://api.charitycommission.gov.uk/register/api/searchCharityName/{text}
• https://api.charitycommission.gov.uk/register/api/allcharitydetailsV2/{number}/{subsidiary}
• https://api.charitycommission.gov.uk/register/api/charityfinancialhistory/{number}/{subsidiary}
• https://api.charitycommission.gov.uk/register/api/charitytrusteeinformation/{number}/{subsidiary}

Things worth knowing:

• Azure API Management 401s, never 403s, on a missing or wrong key, and says so in a WWW-Authenticate: AzureApiManagementKey header — so a key problem is unambiguous and is not confusable with an entitlement lag.
• A wrong path 404s BEFORE the key is checked, which is how the operation names above were confirmed without holding a key. charitytrustees, charityclassification, charitypublishedreport, charityotheraddresses and charityeventhistory all 404 — they do not exist. The real names are charitytrusteeinformation, charityareaofoperation, charitygoverningdocument and charityotherregulators, all of which 401 (i.e. exist).
• Every charity-scoped operation takes TWO path segments: the registered charity number and a subsidiary number. The main charity is 0; omitting the second segment 404s.
• register-of-charities.charitycommission.gov.uk/api/search — the public website's own endpoint — was returning 502 Bad Gateway from the Azure Application Gateway when this pack was built, so it is not a keyless fallback.

Quick Start

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

{
  "mcpServers": {
    "uk-charity-commission": {
      "url": "https://gateway.pipeworx.io/uk-charity-commission/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/uk-charity-commission/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 1684+ 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/ukcharity_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"oxfam","limit":5}'

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

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-uk-charity-commission

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Charity Commission data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT