Skip to main content
Glama

🪐 Colab MCP (模型上下文协议)

Python MCP

一个 MCP (模型上下文协议) 服务器,可将您的本地 AI 智能体无缝连接到浏览器中运行的 Google Colab 会话。

✨ 功能

  • 将本地 AI 助手直接连接到基于浏览器的 Colab 笔记本

  • 支持通过智能体在 Colab 中执行 Python 代码

  • 读取并与 Colab 笔记本状态进行交互

Related MCP server: colab-mcp

💻 支持的客户端

此 MCP 服务器需要一个支持 notifications/tools/list_changed 且必须在您的设备上本地运行的客户端。

符合这些条件的常用客户端包括:

🚀 安装与设置

  1. 安装 uv (一个速度极快的 Python 包安装程序和解析器):

    pip install uv
  2. 配置您的 MCP 客户端 (例如,在您的 mcp.json 或等效配置文件中):

    {
      "mcpServers": {
        "colab-mcp": {
          "command": "uvx",
          "args": ["git+https://github.com/googlecolab/colab-mcp"],
          "timeout": 30000
        }
      }
    }

    谷歌员工(或使用非标准包索引的用户)请注意: 您可能需要在 args 数组中添加 --index https://pypi.org/simple。

💬 问题与讨论

我们使用 GitHub Discussions 作为我们讨论问题和功能请求的主要场所。

当讨论成熟为明确的行动项时,维护者会将其转换为跟踪问题。此工作流程有助于我们确保问题跟踪器保持去重、易于理解且具有高度可操作性。

⚠️ 请不要直接提交 issue。

🤝 贡献

虽然我们感谢社区的关注,但我们目前没有足够的带宽来审查外部贡献。我们希望避免用户的 Pull Request 因缺乏审查而搁置,因此我们目前不接受外部贡献。

如果您有好的想法或遇到痛点,我们非常乐意在我们的 Discussions 页面上听到您的声音!


🛠️ 内部(供 Colab 开发人员使用)

先决条件

  • 需要 uv (pip install uv)

  • 配置 git 钩子以运行存储库预提交检查:

    git config core.hooksPath .githooks

本地开发设置 (Gemini CLI)

要使用 Gemini CLI 测试您的本地检出版本,请使用以下配置:

{
  "mcpServers": {
    "colab-mcp": {
      "command": "uv",
      "args": ["run", "colab-mcp"],
      "cwd": "/path/to/github/colab-mcp",
      "timeout": 30000
    }
  }
}

MCP_Colab

Available Tools

1 tool
open_colab_browser_connectionA

Opens a connection to a Google Colab browser session and unlocks notebook editing tools. Returns a boolean representing whether the connection attempt succeeded

Inputs: no named parameters. Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 1 tool

    Disambiguation1/5

    Only one tool exists, so no ambiguity between tools, but the dimension assesses whether tools can be told apart; with one tool there is no need for disambiguation, but it cannot be 'clearly distinct' from others since there are none.

    Naming Consistency3/5

    With a single tool, naming consistency is not applicable; however, the name is descriptive and follows a reasonable pattern, so a neutral score is given.

    Tool Count2/5

    A single tool seems too few for a server named 'Colab MCP', which suggests a broader purpose. The tool only handles opening a connection, leaving other expected functionalities uncovered.

    Completeness1/5

    The server's domain appears to be Google Colab integration, but only one tool for opening a connection is provided. Missing tools for editing, running cells, managing notebooks, etc., make the surface severely incomplete.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers