What is mcp-compressor AGENTS.md?

Repository guidance for coding agents working on mcp-compressor, a tool that reduces how much MCP server information an AI model receives at once. It covers the project's purpose, layout, public interfaces, and architecture.

Use it when modifying mcp-compressor, its command-line tool, SDKs, generated clients, authentication, proxy server, or tool-compression code.

It gives agents the project context they need before changing code, reducing confusion about where features belong and how the Rust, Python, and TypeScript parts fit together.

How atlassian-labs/mcp-compressor configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to atlassian-labs/mcp-compressor. 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/atlassian-labs/mcp-compressor/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/atlassian-labs/mcp-compressor

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/atlassian-labs/mcp-compressor/agents-md/github.svg)](https://agentmods.dev/instructions/atlassian-labs/mcp-compressor/agents-md)

Your own site

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

Per session 2,199 This file is loaded in full into every session.

When invoked 2,199 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	$0.02199	$0.02199
Opus 5.5	$0.00880	$0.00880
Sonnet 5.5	$0.00440	$0.00440
Haiku 4.5	$0.00220	$0.00220

Measured 29d ago against content hash 6467424c6097, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-compressor 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 29d 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 · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents working in this repository.

Project purpose

mcp-compressor helps agents use large MCP servers without sending every backend tool description and schema to the model up front. It provides:

a Rust CLI MCP proxy (mcp-compressor),
Rust, Python, and TypeScript SDKs,
generated CLI/Python/TypeScript clients,
Just Bash integration,
remote streamable HTTP backend support,
OAuth and dynamic auth-provider support,
local TypeScript tool compression for AI SDK-style tools.

The implementation is Rust-first. Python and TypeScript bindings should stay thin and delegate core behavior to Rust whenever practical.

Repository layout

crates/mcp-compressor/ — public Rust crate and installable mcp-compressor binary.
crates/mcp-compressor-core/ — core Rust implementation: compression, config parsing, MCP runtime, proxy server, OAuth, generated clients, SDK helpers, and FFI DTOs.
crates/mcp-compressor-python/ — PyO3 extension crate backing the Python package.
crates/mcp-compressor-node/ — napi-rs native addon backing the TypeScript package.
python/mcp-compressor/ — public Python package. Public import is mcp_compressor.
typescript/ — public TypeScript package @atlassian/mcp-compressor.
docs/ — public documentation site.
tests/ — repository-level Python integration and real-world tests.

Public API names

Do not leak implementation/migration names into public docs or examples.

Use:

Python package/import: mcp-compressor / mcp_compressor
TypeScript package: @atlassian/mcp-compressor
Rust crate: mcp-compressor / mcp_compressor
CLI: mcp-compressor

Avoid public references to old or internal names such as mcp-compressor-rust, mcp_compressor_rust, or mcp-compressor-core unless you are editing explicitly internal/development documentation.

Run this guard after public API/doc changes:

uv run python scripts/check_public_api_names.py

Core architecture principles

Read the full file on GitHub · 245 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.

29d ago Changed · +5 lines · +99 tokens per session 6467424c6097
2mo ago First seen · 240 lines · 2,100 tokens per session scan A f63bff807955

Subscribe to this mod's changes

mcp-compressor AGENTS.md is an instructions file published in the GitHub repository atlassian-labs/mcp-compressor (141 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,199 tokens to every session, about $0.0088 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 2026-08-30.

mcp-compressor AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-compressor AGENTS.mdatlassian-labs/mcp-compressor	Instructions file	141	2d ago	Apache-2.0	A	2,199	Codex, OpenCode
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

mcp-compressor: Instructions file for Codex