postal MCP Server
andrefetch/postal
[](https://agentrank-ai.com/tool/andrefetch--postal/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) An open-source, terminal-based AI coding agent that reads your code, calls tools, and helps you build.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
andrefetch/postal is a Python tool licensed under GPL-3.0. An open-source, terminal-based AI coding agent that reads your code, calls tools, and helps you build. Topics: agentic-ai, ai, cli, coding-agent, developer-tools, llm, mcp, open-source, openrouter, python, tui-app.
Ranked #593 out of 24846 indexed tools.
In the top 3% of all indexed tools.
Ecosystem
Score Breakdown
121 stars → growing community
Last commit 29d ago → recently updated
12/12 issues closed → responsive maintainer
6 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/andrefetch--postal/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/andrefetch--postal/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/andrefetch--postal" alt="AgentRank"></a> Matched Queries
From the README
<h1 align='center'> Postal </h1> <p align="center"> <b>An open-source AI coding agent that lives in your terminal.</b><br /> Plans, edits, runs, and reviews code with any model on OpenRouter. </p> <p align="center"> </p> Postal connects to LLMs through OpenRouter, reads and edits your code with a built-in tool set, runs shell commands, delegates to specialized sub-agents, and streams everything through a full-screen TUI. Every mutating action goes through an approval policy you control, so it is as autonomous or as careful as you want it to be. ## Motivation I built Postal because I wanted to understand how modern AI coding harnesses actually work: the agent loop, tool calls, context management, approvals, and everything that turns a model into something that can work on a codebase. The harnesses I wanted to learn from were either closed source or written in languages other than Python. I wanted something I could read, take apart, and experiment with in a language I alreaRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.