What is unmcp AGENTS.md?

A repository-specific instruction file for unmcp, documenting installation, command-line use, architecture, linting, formatting, and type-checking commands.

Use it when developing the unmcp command-line tool, which provides direct commands for calling MCP servers. MCP is a standard way for agents to use external tools.

It tells an AI coding agent how this Python project is organised and how changes should be checked before they are accepted.

unmcp AGENTS.md — Instructions file for Codex and OpenCode by Am1n3e: A repository-specific instruction file for unmcp, documenting installa

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/am1n3e/unmcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/Am1n3e/unmcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/am1n3e/unmcp/agents-md.svg)](https://agentmods.dev/instructions/am1n3e/unmcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/am1n3e/unmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/am1n3e/unmcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 613 This file is loaded in full into every session.

When invoked 613 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00613	$0.00613
Opus 5	$0.00307	$0.00307
Sonnet 5	$0.00123	$0.00123
Haiku 4.5	$0.00061	$0.00061

Measured 5d ago against content hash 081fb5383b4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unmcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to AI coding agents when working with code in this repository.

Build & Development Commands

# Install dependencies (uses uv)
uv sync

# Run the CLI
uv run unmcp --help

# Linting & formatting
uv run ruff check .          # lint
uv run ruff check --fix .    # lint with auto-fix
uv run ruff format .         # format

# Type checking
uv run ty check

Architecture Overview

unmcp is a CLI that provides direct command-line access to MCP (Model Context Protocol) servers, bypassing the protocol overhead for simpler workflows.

Two Execution Modes

On-Demand Mode (default): Each tool call spawns a new MCP server process, executes the tool, and exits. Simple but slower for repeated calls.

Persistent Mode: A daemon process keeps the MCP server running, communicating via Unix socket. Tool calls connect to the daemon rather than spawning new processes.

Core Components

cli.py - Click-based CLI with DynamicServerGroup that dynamically creates subcommands from cached tool schemas. Server tools appear as unmcp <server> <tool>.
services/server_manager.py - ServerManager handles server lifecycle: init (discover tools), start (spawn daemon), stop, status.
services/tool_runner.py - ToolRunner executes tools, automatically routing to socket (persistent) or spawning new process (on-demand).
daemon.py - DaemonServer maintains MCP session and exposes it via Unix socket. Accepts JSON-RPC style messages (call_tool, list_tools, shutdown).
mcp_client.py - MCPClient wraps the MCP SDK's stdio transport for one-shot server connections.

Data Flow

unmcp clt init <server> - connects to MCP server, caches tool schemas to .unmcp/servers/<server>.json
unmcp <server> <tool> - CLI looks up cached schema, builds Click command, invokes ToolRunner.call()
ToolRunner checks for socket at .unmcp/sockets/<server>.sock:
- If exists: sends request via socket to daemon
- If not: creates MCPClient, spawns process, calls tool, exits

Read the full file on GitHub · 60 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 60 lines · 613 tokens per session scan A 081fb5383b4b

Subscribe to this mod's changes

unmcp AGENTS.md is an instructions file published in the GitHub repository Am1n3e/unmcp (11 stars, last pushed 5mo ago), licensed MIT. It adds 613 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

unmcp AGENTS.md