Integrate Glean API for Search and Chat

Glean MCP Server is an MCP server implementation that integrates the Glean API, exposing its two core functions - Search and Chat - as MCP tools. Search returns a list of results for a given query, while Chat provides Q&A-style interaction with Glean's chatbot. This lets an AI assistant tap into Glean's enterprise search and conversational answering directly from the chat interface.

Use this connector when your organization already runs Glean as its enterprise search/knowledge platform and you want an AI assistant to query it - searching internal content or asking the Glean chatbot questions - without switching tools.

Do not use it if you don't have a Glean deployment, since it requires a GLEAN_API_KEY and GLEAN_DOMAIN tied to an existing Glean instance. It is also not a general web search tool - it only surfaces what your Glean instance indexes.

The Search tool takes a query string and returns a list of matching results from Glean's index. The Chat tool takes a question or conversational input and returns Glean chatbot's answer.

• Search: returns a list of search results for a given query against your Glean instance
• Chat: Q&A interaction with Glean's chatbot

Build the Docker image:

docker build -t glean-server:latest -f src/glean/Dockerfile .

Add it to claude_desktop_config.json:

{
  "mcpServers": {
    "glean-server": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "GLEAN_API_KEY", "-e", "GLEAN_DOMAIN", "glean-server"],
      "env": {
        "GLEAN_API_KEY": "YOUR_API_KEY_HERE",
        "GLEAN_DOMAIN": "YOUR_DOMAIN_HERE"
      }
    }
  }
}

Teams already using Glean for enterprise search who want its Search and Chat functions available directly inside an AI assistant.