Wikimedia Enterprise docs
Search and read the Wikimedia Enterprise API docs, no account needed
- Pricing
- Free
- Platforms
- API, CLI, vscode
- Runs
- Remotely
- Version
- 1.1.17
- Listing updated
- 2 days ago
About Wikimedia Enterprise docs
Wikimedia Enterprise docs is a free MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
This public server exposes the Wikimedia Enterprise documentation to coding agents and assistants. It searches the guides and OpenAPI definition and returns full pages and endpoints; it calls no Wikimedia Enterprise API itself.
Four tools are offered: search, fetch, list_endpoints and get_endpoint. search and fetch follow the shape ChatGPT requires of a connector, so it also works there. It uses Streamable HTTP, needs no credentials and accepts POST only.
The docs are also published as llms.txt, markdown versions of every guide (append .md) and an OpenAPI file. The Wikimedia Enterprise API itself offers a free account and paid tiers.
Install
Run in a terminal
claude mcp add --transport http docs https://enterprise.wikimedia.com/mcpAdd to Settings → Connectors → Add custom connector
https://enterprise.wikimedia.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"docs": {
"url": "https://enterprise.wikimedia.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"docs": {
"type": "http",
"url": "https://enterprise.wikimedia.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"docs": {
"serverUrl": "https://enterprise.wikimedia.com/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"docs": {
"type": "http",
"url": "https://enterprise.wikimedia.com/mcp"
}
}
}Tools this server provides (4)
Taken from the project documentation; the running server may differ.
- search
- Matches across guide sections, endpoints and response models
- fetch
- Full text for one result id
- list_endpoints
- Every endpoint in reference order
- get_endpoint
- One endpoint with all references resolved
What it does
- Docs search
- Matches across guides, endpoints and response models.
- Full-text fetch
- A guide, endpoint or schema by id.
- Endpoint list
- Every endpoint, filterable by tag.
- Resolved endpoint view
- One endpoint with $refs resolved.
- ChatGPT compatible
- `search` and `fetch` match the connector shape.
Good for
- Find the right snapshot endpoint while coding
- Look up a response field name
- Check rate-limit guidance without leaving the editor
Pricing
Free
Free, no account needed
Prices change. Check enterprise.wikimedia.com before you buy.
Wikimedia Enterprise docs FAQ
Does it need an account?
No. It is public and read-only.
Does it call the API?
No. It only serves documentation.
Which transport?
Streamable HTTP, POST only.
Does it work in ChatGPT?
Yes, as a custom connector with no authentication.
Is Wikimedia Enterprise docs free?
Yes. Wikimedia Enterprise docs is free to use.
How do I add Wikimedia Enterprise docs to Claude Code?
Run this command in your terminal: claude mcp add --transport http docs https://enterprise.wikimedia.com/mcp
What are the best alternatives to Wikimedia Enterprise docs?
The closest alternatives to Wikimedia Enterprise docs are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Wikimedia Enterprise docs

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools