@OthmaneBlial
Basic information
A MCP‑like server using the DeepSeek API for Terminal
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"term_mcp_deepseek": {
"command": "python3",
"args": [
"-m",
"venv",
"venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
An MCP‑like server that uses the DeepSeek API to let AI assistants list tools and execute shell commands via a persistent Bash session. It includes a web chat interface and is designed as a proof-of-concept for the Model Context Protocol ideas. Developers or users who want to enable terminal command execution through an AI chat will find this useful.
Clone the repository, set up a Python virtual environment (3.8+), install dependencies, and configure your DeepSeek API key in .env. Run the server with the startup script (./startup.sh) or manually (python server.py), then access the chat interface at http://127.0.0.1:8000. Docker deployment is also supported via docker-compose up -d. Use the /chat endpoint for AI‑driven command execution or the /mcp/* endpoints for tool discovery and invocation.
/mcp/list_tools and /mcp/call_tool.No. This is a proof‑of‑concept that captures many MCP ideas but does not yet fully comply with Anthropic’s MCP specification. It lacks complete JSON‑RPC support, advanced authentication, and comprehensive error handling needed for production use.
Python 3.8+, pip, and a valid DeepSeek API key are required. The server uses Flask, pexpect, and expects the API key set in a `.env` file.
All data (sessions, conversation state) is stored locally on the machine running the server. No external database is used.
Two transports: HTTP REST API and STDIO command‑line interface. Basic authentication, rate limiting, and security headers are included but are described as “basic” and not production‑grade.
The server is not production‑ready. It lacks full JSON‑RPC protocol support, per‑user session isolation, proper input sanitization, and advanced error handling. Future improvements are planned for protocol standardization, real‑time communication, and modular code architecture.
Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R
Official Porkbun MCP server, maintained by Porkbun. Check domain availability and pricing, register, renew and transfer domains, and manage DNS records, nameservers, URL forwarding, glue records, DNSSEC and domain contac
The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C
One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
Comments