# Google Knowledge Graph

> Google Knowledge Graph is an open-source MCP server for knowledge and memory. Look up people, places and organizations in Google's Knowledge Graph from Claude. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, self-hosted
- **Website:** https://houtini.com
- **Repository:** https://github.com/houtini-ai/google-knowledge-graph-mcp
- **MCP Registry name:** io.github.houtini-ai/google-knowledge-graph
- **Categories:** knowledge and memory, web search and scraping
- **Listing updated:** 2026-11-15

## About

This small server wraps Google's Knowledge Graph Search API so an assistant can verify facts about real-world entities during research. The author built it for fact-checking workflows and notes that the API itself is free, requiring only a Google Cloud API key with no billing account.

It offers two tools. One searches by name or description and returns entity types, descriptions (often drawn from Wikipedia), images, URLs, relevance scores and Machine IDs. The other looks up entities directly by Machine ID, which helps when resolving entities you already have identifiers for.

Install it with npx in Claude Desktop, with claude mcp add in Claude Code, or from source. It is MIT licensed and published by Houtini, a consultancy that also maintains other MCP servers. A GOOGLE_KNOWLEDGE_GRAPH_API_KEY is required.

## Features

- **Entity search:** Search by name or description and get structured results.
- **MID lookup:** Look up entities directly by Google Machine ID.
- **Rich results:** Returns types, descriptions, images, URLs and relevance scores.
- **Free API:** Uses Google's free Knowledge Graph API with a Cloud API key.
- **Easy install:** Runs from npx, Claude Code or a local build.

## Good for

- Verify that a person or organization exists before citing it
- Resolve entity names to Machine IDs
- Pull a short description and Wikipedia link for a topic
- Check entity types during content research

## Install

### Claude Code (Terminal)

```sh
claude mcp add google-knowledge-graph --env GOOGLE_KNOWLEDGE_GRAPH_API_KEY='<GOOGLE_KNOWLEDGE_GRAPH_API_KEY>' -- npx -y @houtini/google-knowledge-graph-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "google-knowledge-graph": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/google-knowledge-graph-mcp"
      ],
      "env": {
        "GOOGLE_KNOWLEDGE_GRAPH_API_KEY": "<GOOGLE_KNOWLEDGE_GRAPH_API_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "google-knowledge-graph": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/google-knowledge-graph-mcp"
      ],
      "env": {
        "GOOGLE_KNOWLEDGE_GRAPH_API_KEY": "<GOOGLE_KNOWLEDGE_GRAPH_API_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "google-knowledge-graph": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@houtini/google-knowledge-graph-mcp"
      ],
      "env": {
        "GOOGLE_KNOWLEDGE_GRAPH_API_KEY": "<GOOGLE_KNOWLEDGE_GRAPH_API_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "google-knowledge-graph": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/google-knowledge-graph-mcp"
      ],
      "env": {
        "GOOGLE_KNOWLEDGE_GRAPH_API_KEY": "<GOOGLE_KNOWLEDGE_GRAPH_API_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "google-knowledge-graph": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/google-knowledge-graph-mcp"
      ],
      "env": {
        "GOOGLE_KNOWLEDGE_GRAPH_API_KEY": "<GOOGLE_KNOWLEDGE_GRAPH_API_KEY>"
      }
    }
  }
}
```

## Tools

- `search_knowledge_graph`: Searches entities by name or description and returns structured data.
- `lookup_knowledge_graph_entities`: Looks up entities by their Machine IDs.

## FAQ

### Does it cost anything?

The README says the Knowledge Graph API is free; you only need a Google Cloud API key.

### What do I need to run it?

Node via npx and a GOOGLE_KNOWLEDGE_GRAPH_API_KEY.

### How many tools?

Two: search_knowledge_graph and lookup_knowledge_graph_entities.

### What is the license?

MIT.

### Is Google Knowledge Graph free?

Yes. Google Knowledge Graph is open source, so you can use and self-host it for free.

### How do I add Google Knowledge Graph to Claude Code?

Run this command in your terminal: claude mcp add google-knowledge-graph --env GOOGLE_KNOWLEDGE_GRAPH_API_KEY='<GOOGLE_KNOWLEDGE_GRAPH_API_KEY>' -- npx -y @houtini/google-knowledge-graph-mcp

### What are the best alternatives to Google Knowledge Graph?

The closest alternatives to Google Knowledge Graph are Scrapling MCP Server, Codebase Memory, XERJ, Firecrawl MCP Server and Claude Code Ultimate Guide.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.

---
Source: https://ai-powered.com/mcp/google-knowledge-graph
