Search Google's Knowledge Graph for structured information about real-world entities
Google Knowledge Graph Search MCP
This MCP server searches Google’s Knowledge Graph for structured information about real-world entities. It is designed as an MCP integration for entity lookup and structured-data retrieval, enabling developers to query knowledge-graph-backed entity information.
🛠️ Key Features
Search Google’s Knowledge Graph for real-world entities
Provide structured information about entities
🚀 Use Cases
Entity search for semantic-search workflows
Entity recognition and structured-data enrichment
Knowledge-graph retrieval to support SEO-oriented crawling
⚡ Developer Benefits
MCP server integration aligned with Model Context Protocol (MCP)
Use as an API client for knowledge-graph entity access
Topics include entity-search, structured-data, and semantic-search
⚠️ Limitations
Description provided does not specify query breadth, result limits, authentication, or response format details beyond “structured information about real-world entities”
Model Context Protocol server that connects Claude (or any MCP client) to Google's free public Knowledge Graph API. Search for real-world entities - people, places, organisations, concepts - and get structured data back.
What is this? An MCP server. If you don't know what that means, you probably don't need this. If you're using Claude Desktop or another MCP-compatible client and want to search Google's knowledge database, this is for you.
Why This Exists
I built this because I needed a way for Claude to verify entity information during research workflows. Google's Knowledge Graph contains structured data about millions of real-world entities - the same data that powers those knowledge panels in Google Search results.
The Knowledge Graph Search API is completely free. No billing account, no usage costs, just a Google Cloud API key. Most developers don't seem to know this exists, which is odd given how useful it is.
This MCP gives Claude (or any MCP client) access to that database.
What You Get
Two tools for searching Google's knowledge graph:
1. Search by query - search_knowledge_graph
Search for entities by name or description. Returns structured data including entity types, descriptions, Wikipedia URLs, and relevance scores.
2. Lookup by MID - lookup_knowledge_graph_entities
If you already have Machine IDs (Google's internal entity identifiers), look them up directly. Useful for entity resolution workflows.
Enable "Knowledge Graph Search API" in the API Library
Navigate to "Credentials" and create an API key
(Optional but recommended) Restrict the key to Knowledge Graph Search API only
That's it. No credit card, no billing setup.
Usage Examples
Once installed and Claude Desktop is restarted, you can:
Basic entity search:
code
Search the knowledge graph for "Marie Curie"
Entity type filtering:
code
Search knowledge graph for "Python" with types ["ComputerLanguage"]
Multiple results:
code
Search knowledge graph for "Paris" limit 5
Lookup by MID:
code
Look up knowledge graph entity /m/0dl567
The MCP returns structured JSON that Claude can parse. You'll get entity names, types, descriptions, URLs, and relevance scores.
What Gets Returned
Example response structure:
json
{"entities":[{"mid":"/m/0dl567","name":"Taylor Swift","type":["Person","Thing"],"description":"American singer-songwriter","detailedDescription":"Taylor Alison Swift is an American singer-songwriter...","image":"https://...","url":"http://en.wikipedia.org/wiki/Taylor_Swift","resultScore":4258.07}],"count":1}
Parameters
search_knowledge_graph
query (required): Search term
languages (optional): Language codes array, e.g. ["en"]
types (optional): Entity types to filter by, e.g. ["Person", "Organization"]
limit (optional): Max results (default 20, max 500)
lookup_knowledge_graph_entities
ids (required): Array of Machine IDs (MIDs), e.g. ["/m/0dl567"]
languages (optional): Language codes array
Common Entity Types
The Knowledge Graph uses schema.org types. Common ones:
Person - Individual people
Organization - Companies, institutions
Place - Locations, geographical entities
Event - Historical or current events
CreativeWork - Books, films, music, art
Product - Commercial products
ComputerLanguage - Programming languages
SportsTeam - Sports teams
Country - Nations and countries
City - Cities and municipalities
You can combine types for more specific searches.
Troubleshooting
MCP not appearing in Claude:
Check your JSON syntax - one error breaks everything
Verify the path uses correct escaping (\\ on Windows)
Completely restart Claude Desktop (quit, not just minimise)
Check the API key environment variable spelling
"API key required" error:
The environment variable isn't being read
Check spelling: GOOGLE_KNOWLEDGE_GRAPH_API_KEY
Restart Claude Desktop after config changes
No results returned:
Try different query terms
Remove entity type filters to broaden search
Check result limit isn't set too low
401 Unauthorized:
API key is invalid or expired
Knowledge Graph Search API isn't enabled in your Google Cloud project
Building From Source
bash
npm install
npm run build
The build process compiles TypeScript to CommonJS in dist/. No special configuration needed.
Technical Details
API Endpoint:https://kgsearch.googleapis.com/v1/entities:search
Response Format: JSON-LD with itemListElement array
Module Format: CommonJS (compatible with Node.js MCP hosts)
Why CommonJS?
The MCP SDK uses CommonJS patterns. I've stuck with that for compatibility. If you're building your own MCP and want ES modules, that's fine - just different choices.
Contributing
If you find issues or have improvements:
Check existing issues first
Test your changes locally
Submit a PR with clear description
I'm particularly interested in hearing about:
Entity types that need better handling
Response parsing edge cases
Real-world usage patterns
Licence
MIT - do what you want with it.
Author
Built by Richard Baxter (Houtini) as part of a collection of MCP servers for AI-assisted development and research workflows.
Other Houtini MCPs:
@houtini/gemini-mcp - Google AI chat with grounding and deep research
@houtini/geo-analyzer - Content optimisation for AI search engines
