MCP server that gives an MCP host a working sub-agent whose brain can be any Anthropic-compatible model
View on GitHub ↗An MCP server that gives a ChatGPT connector (or any other MCP client) a working sub-agent — and, optionally, one that reads files, runs commands, and works a multi-step task to completion on your machine.
It ships pointed at DeepSeek, which is the cheap default rather than the point. The design is model-agnostic: the sub-agent's brain is whatever Anthropic-compatible endpoint you put in DEEPSEEKBASEURL, and the harness around it is a swappable part. That is where the name comes from.
中文说明 · Changelog · Contributing · Security
It puts another working sub-agent inside your ChatGPT conversation — one whose brain can be any model you like.
Be precise about this, because the project gets retold wrong a lot: ChatGPT's own sub-agents (Luna and friends) can already do real work — they read and write files on your machine, run commands, and iterate. This bridge is not filling in a missing capability.
The real constraint sits elsewhere: sub-agent slots only accept OpenAI's own model tiers (Sol / Terra / Luna). An external model cannot be registered as one. So the moment you want a different model doing that work — faster, cheaper, or independent enough to review the implementer — the only door in is an MCP connector.
And an MCP tool is a text interface by default: you call it, you get text back. To let an external model actually work, you have to hand it a whole environment first.
The mechanism matters more than the outcome: it does not plug DeepSeek in, it gives DeepSeek hands. A bridge that only forwards an API hands the host one more model to ask. This one does not — on an
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/CassiaTw1g--modelbridge.html)
TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
BeforeWave/dsh-with-chatgptBring ChatGPT’s reasoning to your local codebase. Work directly, or delegate larger tasks to DSH.
howznguyen/pi-delegate-mcpMCP server that turns the pi coding agent into a steerable background worker: delegate a task, redirect it mid-run, and keep its context out of your own.
oomol-lab/dsh-oomolOOMOL Connector for DeepSeek Harness—discover connected apps and execute Actions through progressive MCP discovery without exposing provider credentials.
liangyou09/lyshellAI-native terminal & SSH client — built-in DeepSeek Harness to launch agents in TUI or embedded Web UI, plus SFTP, serial/Telnet and MCP server.
livetennisapi/livetennisapi-mcpMCP server for the Live Tennis API — give Claude, Cursor and other LLM agents real-time tennis scores, odds and model win-probability
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.