MCP Chat
MCP Chat
MCP Chat 是一个命令行界面应用程序,可通过 Anthropic API 与 AI 模型进行交互式聊天。该应用程序通过 MCP (Model Control Protocol) 架构支持文档检索、基于命令的提示以及可扩展的工具集成。
前提条件
Python 3.9+
Anthropic API Key
Related MCP server: MCP Chat Server
设置
步骤 1:配置环境变量
在项目根目录中创建或编辑
.env文件,并确保以下变量已正确设置:
CLAUDE_MODEL="claude-sonnet-4-5"
ANTHROPIC_API_KEY="" # Enter your Anthropic API secret key
# Set to 1 if you're using uv to run the project
# Set to 0 if you're *not* using uv
USE_UV=1步骤 2:安装依赖项
选项 1:使用 uv 进行设置(推荐)
uv 是一个快速的 Python 包安装器和解析器。
如果尚未安装,请安装 uv:
pip install uv创建并激活虚拟环境:
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate安装依赖项:
uv pip install -e .运行项目
uv run main.py选项 2:不使用 uv 进行设置
创建并激活虚拟环境:
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate安装依赖项:
pip install anthropic python-dotenv prompt-toolkit "mcp[cli]==1.8.0"运行项目
python main.py使用说明
基本交互
只需输入消息并按 Enter 即可与模型聊天。
文档检索
使用 @ 符号后跟文档 ID,以在查询中包含文档内容:
> Tell me about @deposition.md命令
使用 / 前缀执行 MCP 服务器中定义的命令:
> /summarize deposition.md按下 Tab 键时,命令将自动补全。
开发
添加新文档
编辑 mcp_server.py 文件,将新文档添加到 docs 字典中。
实现 MCP 功能
要完整实现 MCP 功能:
完成
mcp_server.py中的 TODO 项在
mcp_client.py中实现缺失的功能
Lint 检查与类型检查
目前未实现任何 lint 或类型检查。
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
- FlicenseBqualityDmaintenanceEnables interactive chat with AI models and document retrieval via the Anthropic API, supporting command-based prompts and MCP tool integrations.2
- FlicenseBqualityCmaintenanceEnables interactive chat with AI models via Anthropic API, supporting document retrieval and extensible command-based tool integrations.2
- FlicenseNot gradedqualityCmaintenanceCommand-line interface for interactive chat with AI models via Anthropic API, supporting document retrieval and command-based prompts through MCP.
- FlicenseAqualityCmaintenanceEnables interactive CLI chat with AI using Anthropic API, supporting document retrieval and command-based prompts via MCP tools.2
Related MCP Connectors
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
OCR, transcription, file extraction, and image generation for AI agents via MCP.
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/IDHaunter/cli_project'
If you have feedback or need assistance with the MCP directory API, please join our Discord server