mcp-server

mcp-server

28
knowledge_and_memoryai_chatbot

The Glean MCP Server is a project that facilitates integration with Glean's enterprise knowledge via the Model Context Protocol. It offers tools for searching company information, employee profiles, and interacting with an AI assistant, supporting various client configurations.

@gleanwork/mcp-server

MCP Server CI Build npm version License

The Glean MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with Glean's enterprise knowledge.

Features

  • Company Search: Access Glean's powerful content search capabilities
  • People Profile Search: Access Glean's people directory
  • Chat: Interact with Glean's AI assistant
  • MCP Compliant: Implements the Model Context Protocol specification

Tools

  • company_search

    Search Glean's content index using the Glean Search API. This tool allows you to query Glean's content index with various filtering and configuration options.

  • chat

    Interact with Glean's AI assistant using the Glean Chat API. This tool allows you to have conversational interactions with Glean's AI, including support for message history, citations, and various configuration options.

  • people_profile_search

    Search Glean's People directory to find employee information.

Configuration

API Tokens

You'll need Glean API credentials, and specifically a user-scoped API token. API Tokens require the following scopes: chat, search. You should speak to your Glean administrator to provision these tokens.

Configure Environment Variables

  1. Set up your Glean API credentials:

    export GLEAN_INSTANCE=instance_name
export GLEAN_API_TOKEN=your_api_token

    Note: For backward compatibility, GLEAN_SUBDOMAIN is still supported, but GLEAN_INSTANCE is preferred.

  2. (Optional) For global tokens that support impersonation:

    export GLEAN_ACT_AS=user@example.com

Client Configuration

You can use the built-in configuration tool to automatically set up Glean for your MCP client:

# Configure for Cursor
npx @gleanwork/mcp-server configure --client cursor --token your_api_token --instance instance_name

# Configure for Claude Desktop
npx @gleanwork/mcp-server configure --client claude --token your_api_token --instance instance_name

# Configure for VS Code
npx @gleanwork/mcp-server configure --client vscode --token your_api_token --instance instance_name

# Configure for Windsurf
npx @gleanwork/mcp-server configure --client windsurf --token your_api_token --instance instance_name

Alternatively, you can use an environment file:

npx @gleanwork/mcp-server configure --client cursor --env path/to/.env.glean

The environment file should contain:

GLEAN_INSTANCE=instance_name
GLEAN_API_TOKEN=your_api_token

After configuration:

  • For Cursor: Restart Cursor and the agent will have access to Glean tools
  • For Claude Desktop: Restart Claude and use the hammer icon to access Glean tools
  • For Windsurf: Open Settings > Advanced Settings, scroll to Cascade section, and press refresh

MCP Client Configuration

To configure this MCP server in your MCP client (such as Claude Desktop, Windsurf, Cursor, etc.), add the following configuration to your MCP client settings:

{
  "mcpServers": {
    "glean": {
      "command": "npx",
      "args": ["-y", "@gleanwork/mcp-server"],
      "env": {
        "GLEAN_INSTANCE": "<glean instance name>",
        "GLEAN_API_TOKEN": "<glean api token>"
      }
    }
  }
}

Replace the environment variable values with your actual Glean credentials.

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

Contributing

Please see for development setup and guidelines.

License

MIT License - see the file for details

Support