What is pigeon-mcp AGENTS.md?

Project instructions for pigeon-mcp, a connector that lets an AI coding agent work with Gmail through the Model Context Protocol (MCP). They describe its setup, structure, commands and coding conventions.

Use them when developing, testing or operating pigeon-mcp, including its local and remote connections to Gmail.

They give the agent the project rules and setup details it needs before changing pigeon-mcp, including which documents to read and which files contain configuration or secrets.

How iXanadu/pigeon-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to iXanadu/pigeon-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/iXanadu/pigeon-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/iXanadu/pigeon-mcp

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/ixanadu/pigeon-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ixanadu/pigeon-mcp/agents-md)

Your own site

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

Per session 925 This file is loaded in full into every session.

When invoked 925 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	$0.00925	$0.00925
Opus 5.5	$0.00370	$0.00370
Sonnet 5.5	$0.00185	$0.00185
Haiku 4.5	$0.00093	$0.00093

Measured 1mo ago against content hash d92441c61747, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pigeon-mcp 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 1mo 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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pigeon-mcp

Project Overview

Gmail connector for MCP: one tool module, two transports (stdio for local harnesses, Streamable HTTP behind a gateway for remote clients). OAuth refresh-token auth, N Gmail identities, server-built MIME, file-path attachments, live signatures.

READ FIRST: docs/specs/gmail-mcp-spec.md (acceptance criteria), then README.md (operator setup), then docs/mailroom.md (one mailbox, many identities — routing and trust rules).

Project Structure

pigeon-mcp/
├── AGENTS.md
├── CLAUDE.md         # symlink -> AGENTS.md
├── src/pigeon_mcp/    # MCP server, config, doctor
├── tests/
├── scripts/          # start/stop/restart, resolve-venv-python
├── docs/specs/       # product spec
├── examples/         # config.example / secrets.example
├── .env              # non-secret (not committed)
├── .keys             # secrets (not committed)
└── pyproject.toml    # entrypoints: pigeon-mcp, pigeon-mcp-http, pigeon-doctor

Commands

pyenv virtualenv 3.13 pigeon-mcp-3.13
pyenv local pigeon-mcp-3.13
pip install -e '.[dev]'
pytest tests/ -v
pigeon-doctor

Conventions

Config: .env (non-sensitive) + .keys (secrets, never commit). Prefix PIGEON_MCP_.
Python: pyenv + pyenv-virtualenv (not python -m venv). Venv name: pigeon-mcp-3.13.
Gmail tokens are gmail-token-*.json under PIGEON_MCP_TOKENS_DIR (default ~/.config/pigeon-mcp/tokens), mode 0640. Owner/tenant state is SQLite (admin.sqlite next to that dir) — not Postgres.
Attachments only from outbox root (default ~/Outbox).
Public routes: /mcp, /oauth/callback, /outbox/stage, GET /inbox/fetch/<ticket> (bearer + single-use ticket), GET /healthz, /~/ (owner passkey dashboard)
Tenants: SQLite admin.sqlite (passkeys, hashed bearers, grants, audit). Gmail refresh tokens stay files. Env bearer seeds tenant grokbot.

Deployment Workflow

Work locally, commit, push
On the server host: sudo -v && ./deploy/deploy.sh (see deploy/DEPLOYING.md) — pull, install, restart, verify, auto-rollback
Marketing-only: ./deploy/deploy-static.sh then purge CDN if pages 404 stale
Record any post-pull host actions for the next operator session

Read the full file on GitHub · 62 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.

1mo ago Changed · +18 tokens per session d92441c61747
2mo ago Changed · +2 lines · +84 tokens per session d3d19733f41c
2mo ago First seen · 60 lines · 823 tokens per session scan A ce2aa9330361

Subscribe to this mod's changes

pigeon-mcp AGENTS.md is an instructions file published in the GitHub repository iXanadu/pigeon-mcp (0 stars, last pushed today), licensed Apache-2.0. It adds 925 tokens to every session, about $0.0037 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.

pigeon-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pigeon-mcp AGENTS.mdiXanadu/pigeon-mcp	Instructions file	0	today	Apache-2.0	A	925	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

pigeon-mcp: Instructions file for Codex