Data · Local MCP server
Google Knowledge Graph
Search Google's Knowledge Graph for structured information about real-world entities.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.houtini-ai/google-knowledge-graph- Version
- 1.0.8
- Status
- Active
- Category
- data
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-10-02
- Updated
- 2026-10-02
- Publisher
- houtini-ai (GitHub) · 8 servers with pages here
- Repository
- github.com/houtini-ai/google-knowledge-graph-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npm | @houtini/google-knowledge-graph-mcp | 1.0.8 | stdio |
How to connect Google Knowledge Graph
Google Knowledge Graph runs locally from a Node.js package published to the npm registry: @houtini/google-knowledge-graph-mcp version 1.0.8. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @houtini/google-knowledge-graph-mcp@1.0.8. It reads the environment variable GOOGLE_KNOWLEDGE_GRAPH_API_KEY (required, secret); set it in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"google-knowledge-graph": {
"command": "npx",
"args": [
"-y",
"@houtini/google-knowledge-graph-mcp@1.0.8"
],
"env": {
"GOOGLE_KNOWLEDGE_GRAPH_API_KEY": "<secret>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from houtini-ai (GitHub)
| Server | Runs |
|---|---|
| Amazon CreatorsAmazon product search returning paste-ready affiliate deal rows for your blog. | Local · stdio |
| FanoutMulti-URL comparative content analysis with topical gap detection. | Local · stdio |
| FmpAccess financial data and market information via Financial Modeling Prep API. | Local · stdio |
| Geo AnalyzerScores content on the signals that get it cited by ChatGPT, Perplexity and AI Overviews. | Local · stdio |
| LmConnect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model. | Local · stdio |
| Seo Audit ConsoleTechnical SEO in Claude: GSC + crawl + DataForSEO - audit, market sizing, content recon. | Local · stdio |
| Seo Crawler MCPCrawl and analyse websites for SEO errors using Crawlee with SQLite storage. | Local · stdio |
More data servers
| Server | Runs |
|---|---|
| Google GscGoogle Search Console MCP: search analytics, URL inspection, site management. | Local · stdio |
| Google Image SearchGoogle Image Search: Fast and Simple Google Images Search API. You can get 100+ search results in. | Remote · HTTP |
| Google JobsGoogle Jobs listings with direct apply links via the Apify Google Jobs Scraper, hosted MCP. | Remote · HTTP |
| Google Jobs (via Apify)Search Google Jobs from AI agents: listings with salaries, full descriptions and apply links. | Remote · HTTP |
| Google Mail MCPGmail over MCP from your own account: search, read threads and messages, labels and drafts. | Local · stdio |
| Google Maps ScraperLive Google Maps business search, review, and photo data for AI agents over MCP. | Remote · HTTP |
| Google ResearcherMCP server providing Google Search, web scraping, and multi-source research tools for AI assistants. | Local · stdio |
| Google ScholarSearch Google Scholar for academic papers, citations, and author profiles. | Remote · HTTP |