What is gunio-mcp CLAUDE.md?

A project instruction file for an unofficial local MCP server and read-only command-line tool for Gun.io, a platform for finding freelance technology work. It documents commands, architecture, authentication, and HTTP serving.

Use it when working on the Gun.io MCP server, running its tests or commands, checking authentication, building its container, or starting its local HTTP mode.

It gives a coding agent the repository-specific rules needed to run, test, and modify the project correctly. It also explains how browser-session authentication and the two-part server setup work.

How InfiniteRoomLabs/gunio-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to InfiniteRoomLabs/gunio-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/InfiniteRoomLabs/gunio-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/InfiniteRoomLabs/gunio-mcp

Made for: Claude Code.

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/infiniteroomlabs/gunio-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/infiniteroomlabs/gunio-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/infiniteroomlabs/gunio-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/infiniteroomlabs/gunio-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/infiniteroomlabs/gunio-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/infiniteroomlabs/gunio-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,393 This file is loaded in full into every session.

When invoked 1,393 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.01393	$0.01393
Opus 5.5	$0.00557	$0.00557
Sonnet 5.5	$0.00279	$0.00279
Haiku 4.5	$0.00139	$0.00139

Measured 2mo ago against content hash 09ec5d173163, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gunio-mcp CLAUDE.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 2mo 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.

CLAUDE.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

An unofficial, local-only MCP server + read CLI for gun.io, authed with the user's own browser session. Business logic is our own Python/FastMCP; the distribution plumbing (cookie broker, wrappers, Docker, installer) was adapted from claudesync (../claudesync). The container runs the Python server; the host-side broker + wrapper mechanism is claudesync's. Read README.md for the security model and install runbook.

Commands

uv sync --extra dev
uv run --extra dev pytest -q                 # full suite
uv run gunio-mcp                             # MCP server over stdio (needs GUNIO_COOKIE)
uv run gunio-mcp --serve                     # streamable HTTP on 127.0.0.1:8000 (remote mode)
uv run gunio me                              # thin read CLI
uv run gunio auth status                     # session health check (read-only)
GUNIO_COOKIE='sessionid=...; csrftoken=...' uv run gunio me   # explicit cookie for dev
docker build --target mcp -t gunio-mcp:local .

Always use uv -- never bare pip/python.

Architecture

Two layers, split like gmail-ai-broker (pure logic vs thin glue):

Path	Role	Purity
`src/gunio_broker/client.py`	`GunioClient`: safety-guarded httpx client for `/api/v2`	glue+guard
`src/gunio_mcp/tools.py`	pure tool helpers (reads + gated writes)	pure
`src/gunio_mcp/server.py`	FastMCP `@mcp.tool` wrappers + `main()` (stdio)	glue
`src/gunio_cli/main.py`	thin read-only typer CLI	glue
`scripts/lib/harvest-cookie.sh`	host-side cookie broker (dual cookie, rookie)	shell
`scripts/lib/gunio-wrapper` / `gunio-fn.fish`	`docker run` wrappers	shell
`scripts/gunio-setup.sh`	installer	shell

Auth: the broker harvests the browser session host-side and passes GUNIO_COOKIE (sessionid=...; csrftoken=...) into the container; the client reads it from env. No Firefox/sqlite reading happens in Python.

Read the full file on GitHub · 82 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.

2mo ago First seen · 82 lines · 1,393 tokens per session scan A 09ec5d173163

Subscribe to this mod's changes

gunio-mcp CLAUDE.md is an instructions file published in the GitHub repository InfiniteRoomLabs/gunio-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,393 tokens to every session, about $0.0056 per session on Opus 5.5. 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.

gunio-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gunio-mcp CLAUDE.mdInfiniteRoomLabs/gunio-mcp	Instructions file	0	2mo ago	MIT	A	1,393	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

gunio-mcp: Instructions file for Claude Code