OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Gemini Webapi MCP

Gemini Webapi MCP is a Python server that exposes Google Gemini chat, image-generation and editing, and file-analysis capabilities to MCP-compatible clients, authenticating through Chrome browser cookies rather than API keys.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Gemini Webapi MCP — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a compatible MCP client to call Gemini for image creation or editing, chat, or file analysis, and can provide the required Chrome-based Gemini authentication.

Who it is for

  • Developers configuring MCP-compatible AI clients to use Gemini tools.
  • Claude Code and Claude Desktop users seeking Gemini image, chat, or file-analysis tasks in their client workflow.

Documented uses

  • Generate images from text prompts through an MCP client.
  • Edit an image with a text prompt and refine it in the same conversation.
  • Ask Gemini to analyze a video URL or a supported uploaded file, such as a PDF.
  • Use Gemini chat models listed by the project: Flash, Pro, and Flash-Thinking.
Before you choose

Requirements & limits

The repository is public and licensed under AGPL-3.0. Its README specifies Python 3.10 or later and Chrome sign-in to Gemini; authentication uses Chrome cookies by default, with manual cookie variables documented as a fallback.

  • Requires an MCP-compatible client and a separately configured local server; configuration paths vary by client.
  • Uses browser cookies rather than API keys, so Gemini sign-in in Chrome is part of setup.
  • The README documents uv installation and standard MCP stdio configuration.
  • Optional Claude Code skill provides prompting tips, tool documentation, and an image-generation guide.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Gemini Webapi MCP with Claude Code

Install the server and register it as an MCP server in Claude Code.

Before you start

  • Python 3.10 or later
  • uv
  • Chrome signed in to gemini.google.com
  • Claude Code

Steps

  1. Sign in to Gemini in Chrome.

  2. Run the command below to install and start the server.

    Documented command
    uv run --with "gemini-webapi-mcp @ git+https://github.com/AndyShaman/gemini-webapi-mcp.git" gemini-webapi-mcp

  3. Register the MCP server with Claude Code using claude mcp add-json gemini '{"command":"uv","args":["run","--with","gemini-webapi-mcp @ git+https://github.com/AndyShaman/gemini-webapi-mcp.git","gemini-webapi-mcp"]}'.

  4. Ask Claude Code for a documented task, such as generating an image with Gemini.

Expected outcome

Claude Code has the Gemini MCP server configuration and can request its documented Gemini tasks.

Guide limitations

  • The server authenticates through Chrome cookies; if automatic cookie detection fails, the README provides a manual-cookie configuration path.
  • This guide follows the repository’s setup instructions and does not verify runtime behavior.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
AndyShaman/gemini-webapi-mcp · Official homepage title · retained in its source language
How we review sourcesSuggest a correction