MCP.so
ログイン

Glean MCP Server

@rahul-roy-glean

Glean MCP Server について

MCP Server for Glean Chat

基本情報

カテゴリ

その他

ランタイム

python

トランスポート

stdio

公開者

rahul-roy-glean

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "glean": {
      "command": "uv",
      "args": [
        "--directory",
        "<PATH_TO_CHECKOUT>",
        "run",
        "glean_server.py"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Glean MCP Server?

A Model Context Protocol (MCP) server that integrates with Glean's Chat API. It allows AI‑assisted tools to query Glean data using a standard MCP interface.

How to use Glean MCP Server?

Clone the repository, create a .env file with GLEAN_API_KEY and GLEAN_BASE_URL, then run uv --directory <PATH_TO_CHECKOUT> run glean_server.py. For integration with Cursor, add the command configuration to ~/.cursor/mcp.json.

Key features of Glean MCP Server

  • Integrates with Glean’s Chat API via MCP.
  • Uses the UV package manager for dependency management.
  • Supports standalone and MCP inspector debug modes.
  • Can be configured with environment variables for credentials.
  • Compatible with Cursor for AI‑powered coding assistance.

Use cases of Glean MCP Server

  • Query company‑specific information (e.g., holiday schedules) from an AI assistant.
  • Integrate Glean’s knowledge base into AI tools like Cursor.

FAQ from Glean MCP Server

What are the prerequisites for Glean MCP Server?

Python 3.10+, the UV package manager, and a Glean API key with permissions to /rest/api/v1/*.

How do I configure Glean MCP Server?

Create a .env file in the project root with GLEAN_API_KEY and GLEAN_BASE_URL (e.g., https://your-domain-be.glean.com/rest/api/v1/).

Can I use Glean MCP Server with Cursor?

Yes. Add a glean entry to ~/.cursor/mcp.json using the uv command as described in the README.

What transport does Glean MCP Server use?

The README does not specify a transport; it is used via stdin/stdout (MCP default) when run as a subprocess, or via the MCP inspector for debugging.

コメント

「その他」の他のコンテンツ