What Do They Know
# whatdotheyknow-mcp
Maintained by BOUCH — private hosting, custom tools and setup: paul@bouch.dev · [bouch.dev/products/whatdotheyknow-mcp](https://bouch.dev/products/whatdotheyknow-mcp)
<!-- mcp-name: io.github.paulieb89/whatdotheyknow-mcp -->
[](https://safeskill.dev/scan/paulieb89-whatdotheyknow-mcp)
[](https://glama.ai/mcp/servers/paulieb89/whatdotheyknow-mcp)
[](https://smithery.ai/servers/bouch/whatdotheyknow)
[](https://vscode.dev/redirect/mcp/install?name=whatdotheyknow&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fwhatdotheyknow-mcp.fly.dev%2Fmcp%22%7D)
[](https://insiders.vscode.dev/redirect/mcp/install?name=whatdotheyknow&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fwhatdotheyknow-mcp.fly.dev%2Fmcp%22%7D&quality=insiders)
[](https://cursor.com/en/install-mcp?name=whatdotheyknow&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vd2hhdGRvdGhleWtub3ctbWNwLmZseS5kZXYvbWNwIn0=)
[](https://vscode.dev/redirect/mcp/install?name=whatdotheyknow&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22whatdotheyknow-mcp%22%5D%7D)
A Model Context Protocol server for UK Freedom of Information research. Connects AI assistants to [WhatDoTheyKnow](https://www.whatdotheyknow.com/) — the UK's largest FOI request platform — to search requests, read responses, look up public authorities, and draft new requests.
## Tools
| Tool | Description |
|------|-------------|
| `search_request_events` | Full-text search of FOI requests and responses via WhatDoTheyKnow's Atom feed. Supports structured expressions (`status:successful`, `body:"Liverpool City Council"`). |
| `search_authorities` | Search UK public authorities by name. Returns slug for use with other tools. |
| `get_request_feed_items` | Fetch the event timeline (sent, response, clarification) for a specific FOI request. |
| `get_request_detail` | Fetch full public request JSON, including status, authority, requester, correspondence events, and attachment metadata where exposed. |
| `get_user_requests` | List a user's visible requests with title, slug, status, authority, dates, and snippets. |
| `get_user_feed_items` | Fetch a user's activity Atom feed as structured entries with readable content text. |
| `get_authority_detail` | Fetch full public authority JSON, including contact/profile fields and request statistics. |
| `build_request_url` | Build a prefilled WhatDoTheyKnow request URL for a given authority and topic. |
| `create_request_record` | Create a request via the write API (requires `WDTK_API_KEY`). |
| `update_request_state` | Update user-assessed state of a request (requires `WDTK_API_KEY`). |
## Resources
| URI template | Returns |
|---|---|
| `wdtk://authorities/{authority_slug}` | Authority profile JSON |
| `wdtk://requests/{request_slug}` | FOI request detail JSON |
| `wdtk://users/{user_slug}` | User profile JSON |
| `wdtk://requests/{request_slug}/feed` | Request event Atom feed |
| `wdtk://users/{user_slug}/feed` | User activity Atom feed |
| `wdtk://authorities/all.csv` | Full CSV of all UK public authorities |
## Prompts
| Prompt | Description |
|--------|-------------|
| `draft_foi_request` | Draft a narrow, specific FOI request for a given authority and topic. |
## Connect
### Hosted (no install)
```json
{
"mcpServers": {
"whatdotheyknow": {
"type": "http",
"url": "https://whatdotheyknow-mcp.fly.dev/mcp"
}
}
}
```
### Local (uvx)
```json
{
"mcpServers": {
"whatdotheyknow": {
"type": "stdio",
"command": "uvx",
"args": ["whatdotheyknow-mcp"]
}
}
}
```
## Environment variables
| Variable | Required | Description |
|----------|----------|-------------|
| `WDTK_API_KEY` | Optional | Enables `create_request_record` and `update_request_state` write tools |
## Upstream API and Licence
| Source | API | Licence | Auth |
|--------|-----|---------|------|
| WhatDoTheyKnow | `www.whatdotheyknow.com` | [OGL v3](https://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/) | None (read) / API key (write) |
Data is sourced directly from the WhatDoTheyKnow public API. The platform is operated by mySociety.
TDQS
Scored across 12 tools
Most tools target clearly distinct resources and actions: request detail vs. authority detail vs. user requests vs. authority search. The main overlap is between feed/event tools that both return AtomEntry-style results, but descriptions clarify which to use. The prompt tools are unrelated to the FOI domain, though not easily confused with the domain tools.
All tool names use consistent snake_case and follow a predictable verb_noun pattern: get_*, search_*, build_*, create_*, update_*, list_*. No naming convention mixing is present.
Twelve tools is a well-scoped size for this domain, covering reads, search, URL building, and limited writes. The two prompt tools are somewhat extraneous, but the overall count remains reasonable and manageable.
The surface covers the core FOI workflows: request detail/feed, user activity, authority search/detail, event search, URL construction, and experimental create/update operations. Minor gaps remain, such as attachment content retrieval, user profile detail, and richer request lifecycle operations, but agents can work around most of them.