Provides tools for searching Wikipedia articles, retrieving full article content, getting summaries, extracting key facts, obtaining geographic coordinates, and accessing related topics and links.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Wikipedia MCP Server summarize the article on Albert Einstein"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server providing access to Wikipedia through 10 tools: search, retrieve articles, summarize content, extract facts, get coordinates, and more.
100% Test Coverage - 31 test cases, full schema validation
Multi-language Support - Access different Wikipedia editions
Robust Error Handling - Graceful API error handling
Related MCP server: Wikipedia MCP Server
Tool | Description |
| Search for articles matching a query |
| Get complete article content |
| Get article summary |
| Get query-focused summary |
| Summarize specific sections |
| Extract key facts from articles |
| Find related articles and categories |
| Get article structure and sections |
| Get all links within an article |
| Get geographic coordinates |
# Install with uvx
uvx --from git+https://github.com/yourusername/wikipedia-mcp-server wikipedia-mcp-server
# Or local development
git clone https://github.com/yourusername/wikipedia-mcp-server.git
cd wikipedia-mcp-server && uv sync{
"mcpServers": {
"wikipedia": {
"command": "uvx",
"args": ["--from", "git+https://github.com/yourusername/wikipedia-mcp-server", "wikipedia-mcp-server"]
}
}
}uv run python test_server.py # 31 tests, 100% pass rateSearch:
{"tool": "search_wikipedia", "arguments": {"query": "AI"}}Get Article:
{"tool": "get_article", "arguments": {"title": "Python (programming language)"}}Extract Facts:
{"tool": "extract_key_facts", "arguments": {"title": "Marie Curie", "topic_within_article": "Nobel Prize"}}This server follows specific design patterns for handling parameters and data types to ensure consistency and predictability.
Schema Pattern: All input parameters are marked as required in JSON schemas
{
"required": ["title", "query", "max_length"]
}Handler Pattern: Functions can have optional parameters with defaults
async def summarize_article_for_query(
title: str,
query: str,
max_length: int = 250 # Default provided in handler
) -> Dict[str, Any]:Benefits:
Clear Client Expectations: MCP clients must provide all documented parameters
Implementation Flexibility: Handlers can use sensible defaults when appropriate
Future Extensibility: Schema can be expanded without breaking existing implementations
Nullable Fields: Use ["type", "null"] only when data genuinely might not exist
{
"coordinates": { "type": ["array", "null"] }, // May not exist for non-geographic articles
"pageid": { "type": ["number", "null"] }, // May be null if article doesn't exist
"error": { "type": ["string", "null"] } // Null on success, string on error
}Non-Nullable Collections: Always return empty arrays instead of null
{
"links": { "type": "array" }, // Returns [] if no links found
"facts": { "type": "array" }, // Returns [] if no facts extracted
"sections": { "type": "array" } // Returns [] if no sections found
}Non-Nullable Strings: Always return empty strings instead of null
{
"summary": { "type": "string" }, // Returns "" if no summary available
"text": { "type": "string" }, // Returns "" if no content available
"title": { "type": "string" } // Always present, never null
}Semantic Nullability: Only use null when it represents "this data doesn't exist" rather than "this data is empty"
Predictable Types: Arrays are always arrays, strings are always strings (unless explicitly nullable)
Client Safety: Clients can safely iterate arrays and concatenate strings without null checks
Clear Intent: Nullable fields have explicit semantic meaning (coordinates for non-places, errors on success, etc.)
Geographic Data (nullable when appropriate):
{
"title": "Programming", // Always string
"coordinates": null, // Null - programming isn't a place
"pageid": 12345, // Number when article exists
"error": null // Null on success
}Content Collections (empty when no data):
{
"title": "Stub Article", // Always string
"links": [], // Empty array - no links found
"facts": [], // Empty array - no facts extracted
"summary": "" // Empty string - no summary available
}This design ensures type safety, predictable behavior, and clear semantic meaning across all tools.
Dependencies: mcp>=1.6.0, wikipedia-api>=0.6.0, requests>=2.31.0, jsonschema>=4.0.0
# Local development
git clone repo && cd wikipedia-mcp-server
uv sync && uv run python test_server.pyProduction-ready Wikipedia MCP server with 100% test coverage.
This server cannot be deployed
Concise English Wikipedia summaries — paid per call (x402/credits), 1 tools
Wikipedia, Wikidata and Wiktionary as clean JSON, not HTML. 1.9M searchable. Free, no auth.
Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.
Search and fetch Wikidata entities, execute SPARQL queries, and resolve external identifiers.
