python-sdk AGENTS.md

A set of instructions for AI coding agents working on the Model Context Protocol Python SDK, a software library for building connections between AI systems and tools.

In plain words
What is it for?
Use it when changing the SDK, adding packages, preparing pull requests, or deciding whether a change belongs on the stable or maintenance branch.
Why use it?
It helps agents follow the repository’s contribution rules, versioning promises, branch policy, package manager, and code-quality expectations.

Instructions file for CodexOpenCode

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/modelcontextprotocol/python-sdk/agents-md
Clone the repo
git clone --depth 1 https://github.com/modelcontextprotocol/python-sdk

Made for: Codex, OpenCode.

Per session 2,207 This file is loaded in full into every session.
When invoked 2,207 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.

ModelPer sessionOnce invoked
Fable 5 $0.02207 $0.02207
Opus 5 $0.01104 $0.01104
Sonnet 5 $0.00441 $0.00441
Haiku 4.5 $0.00221 $0.00221

Measured yesterday against content hash 26457e8cd68b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

python-sdk 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 yesterday.

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 · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Guidelines

Note for AI Agents

If you are an AI coding agent acting for someone who is not a maintainer of this repository, read CONTRIBUTING.md before opening issues or pull requests here. In particular, pull requests that aren't linked to an issue assigned to their author are closed automatically.

Branching Model

  • main is the current stable line (v2); releases are cut from it (see RELEASE.md).
  • v2 is released; its public API is a compatibility contract for the 2.x line. Removals, renames, or any change to an existing API's signature or observable behaviour (including ones softened by a @deprecated shim) is a design decision a maintainer makes explicitly, and should generally be avoided.
  • docs/migration.md is the v1 → v2 record and is closed to new entries. Correcting errors or improving clarity in what's there is fine.
  • v1.x is the maintenance branch for the previous major. Backport PRs target it and use a [v1.x] title prefix; only critical bug fixes and security fixes land there.
  • README.md documents v2. The v1 README lives on the v1.x branch.

Package Management

  • ONLY use uv, NEVER pip
  • Installation: uv add <package>. Exception: the root project's runtime dependencies are dynamic (the published mcp wheel exact-pins mcp-types), so uv add cannot edit them — add the requirement to [tool.hatch.metadata.hooks.uv-dynamic-versioning].dependencies in pyproject.toml by hand, then run uv lock. Dependency groups, extras, and the example packages still take plain uv add.
  • Running tools: uv run --frozen <tool>. Always pass --frozen so uv doesn't rewrite uv.lock as a side effect.
  • Cross-version testing: uv run --frozen --python 3.10 pytest ... to run against a specific interpreter (CI covers 3.10–3.14).
  • Upgrading: uv lock --upgrade-package <package>
  • FORBIDDEN: uv pip install, @latest syntax
  • Don't raise dependency floors for CVEs alone. The >= constraint already lets users upgrade. Only raise a floor when the SDK needs functionality from the newer version, and don't add SDK code to work around a dependency's vulnerability. See Kludex/uvicorn#2643 and python-sdk #1552 for reasoning.

Read the full file on GitHub · 167 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.

  1. yesterday First seen · 167 lines · 2,207 tokens per session scan A 26457e8cd68b

Subscribe to this mod's changes

python-sdk AGENTS.md is an instructions file published in the GitHub repository modelcontextprotocol/python-sdk (24,160 stars, last pushed 3d ago), licensed MIT. It adds 2,207 tokens to every session, about $0.0110 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 2026-08-30.

Related

Other instructions, from other repositories