Skip to main content
Glama
Sign In
FastMCP Google Docs Manager

FastMCP Google Docs Manager

by chronis10
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

đź“„ FastMCP Google Docs Manager

Manage Google Docs using a FastMCP API server for Gemini-CLI. Supports listing documents, reading content, and creating new docs.

🚀 Features

  • List Google Docs files

  • Read document content

  • Create new documents with title and content

Related MCP server: Google Docs MCP Server

🔧 Setup

Install Dependencies

pip install uv
cd gemini-tasks-mcp
uv venv
source .venv/bin/activate
uv run main.py

Generate Google API Credentials

  1. Go to Google Cloud Console.

  2. Create a project and enable Google Docs API and Google Drive API.

  3. Go to APIs & Services → Credentials.

  4. Click “Create Credentials” → “OAuth client ID” → Application type: Desktop App.

  5. Download credentials.json and place it in the project folder.

Gemini-CLI Configuration

cd ~/.gemini
nano settings.json
"mcpServers": {
    "docsManager": {
      "command": "uv",
      "args": ["run", "main.py"],
      "cwd": "<<full-path>>/gemini-docs-mcp",
      "timeout": 20000
    }
}

❤️ Powered by FastMCP + Google Docs API + Google Drive API

Available Tools

3 tools
create_documentB

Create a new Google Doc with a title and body content.

Inputs: title (required), content (required). Returns: object

list_documentsB

List Google Docs files from your Google Drive.

Inputs: max_results. Returns: result

read_documentB

Read the text content of a Google Doc by its document ID.

Inputs: doc_id (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.4/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: create_document for creation, list_documents for listing, and read_document for reading content. There is no overlap or ambiguity in their functions, making it easy for an agent to select the correct tool.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (create_document, list_documents, read_document) with no deviations. The naming is predictable and readable throughout the set.

    Tool Count3/5

    With only 3 tools, the server feels thin for a Google Docs manager, as it lacks update and delete operations. While the tools cover basic CRUD aspects (create, list, read), the count is borderline low for the apparent scope of document management.

    Completeness3/5

    The tool set covers create, list, and read operations, but there are notable gaps such as update_document and delete_document for full lifecycle management. Agents can work around this for basic tasks, but the surface is incomplete for comprehensive document handling.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers