mcpterm
a cli for interacting with mcp servers using your favourite llms
Documentation
mcpTerm
a cli for interacting with mcp servers using your favourite llm providers,
*currently only supports deepseek
installation
ensure that you have uv installed or install it with
curl -LsSf https://astral.sh/uv/install.sh | sh
# for linux or mac userspowershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
#for windows usersgit clone https://github.com/VivekMara/mcpTerm && cd mcpTerm && uv syncadd a .env file in the same project directory with the key name "deepseek-api-key"
running
uv run main.pyto use your own mcp servers, simply add the mcp server file into the mcp_servers directory.
Frequently asked questions
What is mcpterm?
mcpterm is a cli for interacting with mcp servers using your favourite llms
How do I install mcpterm?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcpterm open source?
Yes — it is hosted on GitHub at https://github.com/VivekMara/mcpTerm.
Related MCP tools
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to
🚀 The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。 for the Model Context Protocol. Enhance AI assistants with po
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP