# Wikimedia Enterprise Docs MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.wikimedia.enterprise%2Fdocs
Registry id: `mcp-registry/com.wikimedia.enterprise/docs`
Status: live (checked 2026-10-26T18:12:21.372Z)

## Verdict

Wikimedia Enterprise Docs MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 1271 ms median handshake and 2 outages in 90 days. Its agent-readiness grade is A (95/100) across 4 tools, costing an agent about 752 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 1271 ms | 14% of MCP servers |
| p95 handshake latency | 3942 ms | — |
| Checks in 30 days | 4,857 | — |
| Outages, 90 days | 2 | — |
| Median recovery | 9 min | — |
| Agent-readiness score | 95/100 (A) | 80% of MCP servers |
| Tools | 4 | — |
| Tool-list size for an agent | ~752 tokens | 80% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "wikimedia-enterprise-docs-mcp-server": {
      "type": "http",
      "url": "https://enterprise.wikimedia.com/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http wikimedia-enterprise-docs-mcp-server https://enterprise.wikimedia.com/mcp
```

## Tools (4)

- `fetch`: Full text for one id from `search`: `docs/<slug>` (a guide, as markdown; a `#section` suffix is accepted; `docs/changelog` is the release notes and `docs/pricin
- `get_endpoint`: The exact request and response shape of one endpoint, dereferenced from the OpenAPI definition (the source of truth), as structured JSON plus a markdown renderi
- `list_endpoints`: Every endpoint in the Wikimedia Enterprise OpenAPI definition, in reference order, with its technical title, its plain-language line and a link into the referen
- `search`: Full-text search over the Wikimedia Enterprise API documentation: guide sections, the changelog, pricing, endpoints and response models. Exact tokens work best 

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.