Glean MCP
A Model Context Protocol server that provides AI assistants with access to Glean's enterprise knowledge features, including content search, people directory, and AI chat capabilities.
What is Glean MCP?
Glean MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that provides ai assistants with access to glean's enterprise knowledge features, including content search, people directory, and ai chat capabilities.
A Model Context Protocol server that provides AI assistants with access to Glean's enterprise knowledge features, including content search, people directory, and AI chat capabilities.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol server that provides AI assistants
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @gleanwork/mcp-server-utilsManual Installation
npx -y @gleanwork/mcp-server-utilsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Glean MCP
The Glean MCP Server connects AI assistants to your organization's Glean enterprise knowledge base, enabling real-time search across company content, people directories, and documents. It exposes four core tools — company search, people profile search, AI chat, and document reading — so developers and knowledge workers can query internal knowledge directly from their MCP client without leaving their workflow. This server is ideal for teams that rely on Glean as their central enterprise search platform and want to surface institutional knowledge inside Claude or other MCP-enabled assistants.
Prerequisites
- Node.js 18 or later installed
- A Glean account with API access enabled by your Glean administrator
- A Glean API token (obtain from your Glean admin or Settings > API tokens)
- Your Glean server URL (typically https://<your-domain>-be.glean.com)
- An MCP client such as Claude Desktop or Cursor
Obtain your Glean API token
Log in to your Glean workspace, navigate to Settings, and generate a personal API token. Your Glean administrator may need to enable API access for your account. Note your server URL — it usually follows the pattern https://<company>-be.glean.com.
Test the server runs via npx
Verify you can launch the server locally before configuring your MCP client. Run the command below and confirm no errors appear. Pass your credentials as environment variables.
GLEAN_SERVER_URL=https://your-company-be.glean.com GLEAN_API_TOKEN=your_token npx -y @gleanwork/local-mcp-serverAdd the server to your MCP client configuration
Open your Claude Desktop configuration file at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS and add the Glean server entry. Replace the placeholder values with your real server URL and API token.
{
"mcpServers": {
"glean": {
"command": "npx",
"args": ["-y", "@gleanwork/local-mcp-server"],
"env": {
"GLEAN_SERVER_URL": "https://your-company-be.glean.com",
"GLEAN_API_TOKEN": "your_glean_api_token"
}
}
}
}Restart your MCP client
Fully quit and reopen Claude Desktop (or your chosen MCP client) so it picks up the new server configuration. The Glean server will appear in the connected tools list.
Verify the connection
Ask your AI assistant a question that requires searching internal company knowledge. If you receive a meaningful answer drawn from Glean, the server is working correctly.
Glean MCP Examples
Client configuration
Add this block to your claude_desktop_config.json to enable the Glean MCP server with the required environment variables.
{
"mcpServers": {
"glean": {
"command": "npx",
"args": ["-y", "@gleanwork/local-mcp-server"],
"env": {
"GLEAN_SERVER_URL": "https://your-company-be.glean.com",
"GLEAN_API_TOKEN": "your_glean_api_token"
}
}
}
}Prompts to try
Once connected, use these prompts to exercise the four tools: company_search, people_profile_search, chat, and read_documents.
- "Search our internal knowledge base for the Q3 onboarding documentation"
- "Find the employee profile for our Head of Engineering"
- "Use Glean Chat to summarize our latest product roadmap"
- "Read the document at this Glean URL and give me a bullet-point summary: <url>"Troubleshooting Glean MCP
Authentication error or 401 response when the server starts
Double-check that GLEAN_API_TOKEN is set correctly and has not expired. Also confirm GLEAN_SERVER_URL points to your backend URL (the -be subdomain), not the main Glean frontend URL.
Server starts but returns no results for searches
Ensure your Glean API token has the correct scopes for search and chat. Contact your Glean administrator to verify API permissions are enabled for your account and that content has been indexed.
npx command not found or version mismatch
Confirm Node.js 18+ is installed by running node --version. If using nvm, ensure the correct version is active in your shell profile so Claude Desktop can find it.
Frequently Asked Questions about Glean MCP
What is Glean MCP?
Glean MCP is a Model Context Protocol (MCP) server that model context protocol server that provides ai assistants with access to glean's enterprise knowledge features, including content search, people directory, and ai chat capabilities. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Glean MCP?
Install via npm with the command: npx -y @gleanwork/mcp-server-utils. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Glean MCP?
Glean MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Glean MCP free to use?
Yes, Glean MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Glean MCP Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Glean MCP? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Glean MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Glean MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.