Free Tool · Open-Source MCP Server

Google Knowledge Panel
MCP Server

Let Claude see what Google's Knowledge Graph holds for any brand, person or organization, how that entity connects to the real world, and what it still needs to earn a stronger knowledge panel.

Works with Claude Desktop, Claude Code, Cursor, VS Code and any other MCP client. Free and MIT-licensed. Uses a free Google API key, or Wikidata only without one.

Overview

What it does

The server gives your AI assistant four read-only tools. Each one pulls live data from the Google Knowledge Graph Search API and Wikidata.

find_entities

Find every entity behind a name

Lists every Knowledge Graph entity matched for a name, with its ID (e.g. /m/0dr90d), type, description and Google's result score, highest first.

analyze_entity_prominence

See which entity is strongest

Ranks same-name entities on a transparent 0–100 prominence score and explains each score in plain English.

compare_entities

Benchmark competitors

Compares 2–5 brands or people side by side: prominence, readiness, what each is missing, key connections and official profiles, and who leads on each signal.

get_entity

Audit one entity

Returns a full profile: knowledge panel data, connections (founders, CEO, HQ, products, parent company…), official profiles, an 8-point readiness checklist and ready-to-paste JSON-LD.

Under the hood

How it works

1
You ask a question
For example: “Compare HubSpot and Salesforce. Who has the stronger entity?” You don't need to name a tool.
2
Claude picks a tool
It reads the four tool descriptions and calls the right one, here compare_entities with ["hubspot", "salesforce"].
3
The server fetches live data
It queries the Google Knowledge Graph Search API and Wikidata, links the two through the entity's Knowledge Graph ID, and calculates the scores.
4
Claude explains the results
The server returns JSON, and Claude turns it into a plain-language answer. Follow-up questions can chain more tool calls.

Setup

How to install

You need Node.js 18 or newer. The first run downloads and builds the server, which takes about a minute.

Step 1: Get a free Google API key (recommended)

Without a key, the server uses Wikidata only. That covers well-known entities, but many people and smaller brands exist in Google's Knowledge Graph and not in Wikidata.

1
Open the Google Cloud Console
Go to console.cloud.google.com and create or pick a project.
2
Enable the Knowledge Graph Search API
APIs & Services → Library → search for “Knowledge Graph Search API” → Enable.
3
Create an API key
APIs & Services → Credentials → Create credentials → API key.
4
Restrict the key
Restrict it to the Knowledge Graph Search API. The free quota is 100,000 requests a day.

Step 2: Add it to your AI assistant

Replace your-key-here with your key. Your key stays on your computer: it's only sent to Google's API.

Claude Code: run this in your terminal

terminal
claude mcp add knowledge-panel -e GOOGLE_KG_API_KEY=your-key-here -- npx -y github:theseoriddler/google_knowledge_panel_mcp

Claude Desktop and Cursor

In Claude Desktop, open Settings → Developer → Edit Config, add this block, then fully restart the app. In Cursor, add it to ~/.cursor/mcp.json.

claude_desktop_config.json
{
  "mcpServers": {
    "knowledge-panel": {
      "command": "npx",
      "args": ["-y", "github:theseoriddler/google_knowledge_panel_mcp"],
      "env": { "GOOGLE_KG_API_KEY": "your-key-here" }
    }
  }
}

VS Code (GitHub Copilot)

Add this to .vscode/mcp.json.

.vscode/mcp.json
{
  "servers": {
    "knowledge-panel": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "github:theseoriddler/google_knowledge_panel_mcp"],
      "env": { "GOOGLE_KG_API_KEY": "your-key-here" }
    }
  }
}

Step 3: Check it works

Ask: “Use find_entities to look up nike.” If the reply's source says Google Knowledge Graph + Wikidata, your key is working. If it says Wikidata only, check the key in your config and restart the app.

Try it

Example prompts

Find every Knowledge Graph entity for “sara taher”. Which one is strongest?
Which “tesla” entity has the strongest Knowledge Graph presence, and why?
Compare HubSpot, Salesforce and Zoho. Who has the strongest entity, and what is each missing?
Get the full profile of /m/0dr90d, including its connections.
Generate Organization schema for Nike from its knowledge graph data.

Scoring

How entities are scored

The readiness checklist

The readiness score is the share of these 8 checks an entity passes. Without an API key, the three Google checks are skipped.

  • Has a Google Knowledge Graph entry
  • Has a Google description
  • Linked to a detailed source (e.g. Wikipedia)
  • Has an entity image
  • Has an official website
  • Has a Wikidata item
  • Has a Wikipedia article
  • Has 2+ linked official profiles (sameAs)

The prominence score

A transparent 0–100 heuristic, not a Google metric. Signals that aren't available are left out and the rest re-weighted.

SignalWeightFull marks
Google result score, relative to the top match40Top match
Knowledge panel fields (description, detailed source, image, website)20All 4
Wikipedia language editions20100+
Wikidata statements101,000+
Linked official profiles105+

Output

Ready-to-paste schema

get_entity builds Organization or Person JSON-LD with sameAs links from the entity's actual graph data. Here's the output for Tesla (/m/0dr90d), trimmed. Review the links before you publish.

jsonLd
{
  "@context": "https://schema.org",
  "@type": "Organization",
  "@id": "https://www.tesla.com/#organization",
  "name": "Tesla",
  "description": "American automotive, energy storage and solar power company",
  "url": "https://www.tesla.com/",
  "logo": "https://commons.wikimedia.org/wiki/Special:FilePath/Tesla%20Motors.svg",
  "sameAs": [
    "https://en.wikipedia.org/wiki/Tesla,_Inc.",
    "https://www.wikidata.org/wiki/Q478214",
    "https://www.google.com/search?kgmid=%2Fm%2F0dr90d",
    "https://x.com/Tesla",
    "https://www.linkedin.com/company/tesla-motors/",
    "https://github.com/teslamotors"
  ]
}

Good to know

Google's search doesn't always return the obvious entity. For example, salesforce returns Salesforce Marketing Cloud, not Salesforce, Inc. compare_entities works around this by preferring exact name matches. With the other tools, run find_entities first and pass the right ID.

Connections and official profiles come from Wikidata. If an entity has no Wikidata item, those sections are empty, and adding one is one of the most effective ways to strengthen an entity. This project isn't affiliated with or endorsed by Google. Full documentation and troubleshooting are in the GitHub README.