Wikipedia MCP Server 📚

Surgical, token-efficient Wikipedia knowledge retrieval MCP server for AI agents with deterministic summary, search, and full-article projection.

🌐 Live Documentation & Web Portal: https://wikipedia.builditwithai.xyz

⚡ Quickstart

# 1-Line Universal Installer (Auto-configures Claude Desktop, Cursor, Claude Code, Antigravity, VS Code, Zed, Windsurf)
curl -fsSL "https://wikipedia.builditwithai.xyz/install" | bash

# Or run directly via your preferred runtime:
uvx mcp-server-wikipedia
npx -y mcp-server-wikipedia

🤖 Client Setup

A. Claude Code (CLI)

claude mcp add wikipedia -- uvx mcp-server-wikipedia

B. Cursor & Google Antigravity (`mcp.json`)

{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": ["mcp-server-wikipedia"]
    }
  }
}

C. Claude Desktop (`claude_desktop_config.json`)

{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": ["mcp-server-wikipedia"]
    }
  }
}

D. VS Code (Cline / Roo Code / Continue)

{
  "mcpServers": {
    "wikipedia": {
      "command": "npx",
      "args": ["-y", "mcp-server-wikipedia"]
    }
  }
}

🛠️ Tools & Capabilities

Tool Name	Parameters	Description	Return Type
`get_summary`	`title` (string), `lang` (optional)	Fetches concise, factual lead summary of any Wikipedia page.	`string`
`get_article`	`title` (string), `lang` (optional)	Fetches complete article body formatted in clean, structured Markdown.	`string`
`search`	`query` (string), `limit` (int), `lang` (optional)	Searches Wikipedia articles with autocomplete and relevance ranking.	`JSON`
`get_section`	`title` (string), `section_title` (string), `lang` (optional)	Retrieves a specific section by header name, saving context window space.	`string`
`get_links`	`title` (string), `lang` (optional)	Extracts outgoing cross-reference links from an article.	`JSON`
`get_categories`	`title` (string), `lang` (optional)	Lists taxonomic categories and classifications for a page.	`JSON`
`skill_read`	`skill_name` (string)	Dynamically loads research playbooks from GitHub.	`Markdown`
`skills_list`	(none)	Lists all available Wikipedia research skills.	`JSON`

🔒 Telemetry & Privacy

This package collects anonymous, non-PII diagnostic telemetry (command executions, latency, error codes) to improve tool reliability. No article search terms, personal data, source code, or environment variables are ever collected or stored.

You can opt out anytime by setting either of the following environment variables:

export DO_NOT_TRACK=1
# or
export MCP_TELEMETRY_OPT_OUT=1

📄 License

MIT License. See LICENSE for details.

Metadata

Release files for mcp-server-wikipedia 0.5.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp-server-wikipedia 0.5.5
File	Size	Uploaded
mcp_server_wikipedia-0.5.5.tar.gz	31.5 kB	Oct 3, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for mcp-server-wikipedia 0.5.5
File	Interpreter	ABI	Platform	Reset
mcp_server_wikipedia-0.5.5-py3-none-any.whl 25.1 kB Oct 3, 2026	Python 3	none	any	Details

Total release size: 56.6 kB

Release files / mcp_server_wikipedia-0.5.5.tar.gz

Download URL	mcp_server_wikipedia-0.5.5.tar.gz
Size	31.5 kB
Tags	Source
SHA-256 checksum How to use checksums	`e01c5fbf6ae81984d336a2eec6d70eade149e3314793e9b8a67104cfaf3028f1`
BLAKE2b-256 checksum How to use checksums	`489d40c225e5d7cc6a464df4d1dc42f0652668829c0127fcbcbcdf3f778c81c3`
Upload date	Oct 3, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Release files / mcp_server_wikipedia-0.5.5-py3-none-any.whl

Download URL	mcp_server_wikipedia-0.5.5-py3-none-any.whl
Size	25.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`27af3d10aa60603ebdd1706c7b8b125a89deb6357e606639e073eda2df6f17d8`
BLAKE2b-256 checksum How to use checksums	`b159f99398a645087585a424e81b131cedd46578ae2fe98de759f01ee0a0e463`
Upload date	Oct 3, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.13.14`