📡 MCP Radar

howznguyen/pi-delegate-mcp

MCP 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.

13 stars
4 forks
TypeScript
momentum ▲ 40.5
created 2026-08-25
on radar since 2026-08-27
star trend 6 → 13 since 2026-08-27
ai-agentsclaude-codecoding-agentdeepseekllmmcpmcp-servermodel-context-protocolnodejsopenrouterpisubagenttypescript
View on GitHub ↗Homepage ↗

About pi-delegate-mcp

MCP server that exposes the pi coding agent as a delegable, steerable worker.

Point Claude Code (or any MCP host) at it and delegate work to any of pi's ~38 providers (DeepSeek, Grok, GLM, Kimi, Qwen, Codex, OpenRouter, local llama.cpp) with the sub-agent's context staying out of your main conversation.

Your main harness runs on an expensive model, with a context window you care about. A lot of what it does doesn't need that model, and actively damages that context: grepping a repo for every call site, reading a 2000-line file to answer one question, auditing what a refactor left behind.

- Cost. The grunt work runs on DeepSeek, GLM, Kimi, Qwen, or a local llama.cpp. You pay frontier prices only for the reasoning that actually needs them. - Context. The delegate reads the files on its own budget and returns a result. The 200 KB it read never enters your conversation. - Blast radius. Delegates are read-only by default (read, grep, find, ls), enforced at session construction. A cheap model doing exploratory work cannot touch your tree unless you opt it in.

The delegate is always the pi agent. Codex, Grok, DeepSeek and the rest supply the model behind it; this is not a wrapper around their CLIs.

Why pi, and not opencode or a CLI wrapper?

A delegate is only steerable if two channels stay open: you must be able to redirect it mid-task, and it must be able to ask you something and block until you answer. Most ways of driving a coding agent from another program close both.

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/howznguyen--pi-delegate-mcp.html)

Related MCP servers

Cripacx/mediagen

AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with EU AI Act content marking.

⭐ 56TypeScript
syouro/InkPaw

An MCP server and deterministic DOCX toolkit for AI agents—create, edit, validate, and render reliable Word documents with a local agent playground.

⭐ 3JavaScript
0xwilliamortiz/openclaude-improved

runs anywhere. uses anything

⭐ 563TypeScript
LilithGames/a2wave

Turn the agent CLIs you already use into shared services your whole team can call. Natural-language-driven agent orchestration for Claude Code, Cursor Agent, and OpenAI Codex.

⭐ 18TypeScript
luckeyfaraday/frontier-orchestrator

Multi-agent orchestration for Claude Code: MCP server + skill that keeps Claude as lead engineer while delegating backend work to OpenAI Codex and frontend/design work to Kimi

⭐ 6TypeScript
replenhq/replen

Smarter AI Development Workflows

⭐ 5TypeScript

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.