conda-cli-mcp
conda-cli-mcp
conda-cli-mcp 通过模型上下文协议(Model Context Protocol)暴露已安装的 conda 命令行。它在启动时发现内置命令和插件贡献的命令,从 conda 的 argparse 定义创建结构化工具,并通过一个显式启用的原始 argv 工具保持完整 CLI 可访问。
服务器在有界子进程中运行 conda。conda 仍然负责配置、插件排序、求解、事务、报告器、认证、钩子和错误处理。
当目标环境中安装了 conda-completion 0.3 或更新版本时,一个只读元数据工具会通过该插件的公共 Python API 暴露其特定于命令的补全提示。
该项目是 alpha 软件。它需要 Python 3.10 或更新版本,并支持目标 conda 版本 >=26.7,<27。
安装
将已发布的命令安装到隔离环境中:
pipx install conda-cli-mcp将服务器环境与目标 conda 安装分开,并使用 --conda-exe 选择该安装。
Related MCP server: AWS MCP Server
文档
文档按用途组织:
文档发布在 jezdez.github.io/conda-cli-mcp。
安全性
默认策略是只读。--allow-write 允许 conda 管理的变更。--allow-exec 允许 conda run、不透明的透传参数以及原始 conda_execute 工具。策略在启动时固定,并在 conda 启动前强制执行。
运行服务器
当目标 conda 可执行文件位于另一个环境中时,显式选择它:
conda-cli-mcp --conda-exe /absolute/path/to/conda如果没有 --conda-exe,解析会检查 CONDA_EXE,然后检查 PATH。MCP 客户端通过标准输入和标准输出连接。有关客户端配置,请参阅入门教程。
项目范围
conda-cli-mcp负责本地 conda CLI 的发现和执行。conda-meta-mcp负责只读的包和生态系统元数据。conda-mcp保留给未来的伞形包,该包将同时安装两者。
开发
开发、文档和打包使用 Pixi:
pixi install
pixi run test
pixi run check
pixi run -e docs docs
pixi run -e build packageconda 配方是 noarch Python,位于 recipe/recipe.yaml。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that allows secure execution of pre-approved commands, enabling AI assistants to safely interact with the user's system.11122ISC
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to execute AWS CLI commands and access AWS documentation, resources, and prompt templates through the Model Context Protocol with support for Unix pipes and secure Docker-based deployment.MIT
- AlicenseNot gradedqualityCmaintenanceProvides secure, sandboxed terminal access for AI assistants via the Model Context Protocol, with multi-layer risk analysis and auditable command execution.207MIT
- AlicenseDqualityDmaintenanceEnables AI assistants to manage cloud infrastructure using Pulumi by running commands like preview, deploy, and stack output retrieval through the Model Context Protocol.53,690Apache 2.0
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Runtime permission, approval, and audit layer for AI agent tool execution.
A Model Context Protocol server for Wix AI tools
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jezdez/conda-cli-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server