What is python-mcp-server AGENTS.md?

A project-specific AGENTS.md instruction file for a Python MCP server. It documents eight implemented tools that inspect Python projects, such as finding entry points, API endpoints, dependencies, side effects, errors, public APIs, tests, and domain terms.

Use it when contributing to or reviewing this Python MCP server, especially its static-analysis tools and shared analyzer utilities.

It gives an agent the project's context, dependencies, and tool registry so it can work within the repository's existing structure.

How aferreiraguido/python-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to aferreiraguido/python-mcp-server. 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/aferreiraguido/python-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/aferreiraguido/python-mcp-server

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/aferreiraguido/python-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/aferreiraguido/python-mcp-server/agents-md)

Your own site

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

Per session 820 This file is loaded in full into every session.

When invoked 820 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	$0.00820	$0.00820
Opus 5.5	$0.00328	$0.00328
Sonnet 5.5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 2mo ago against content hash 2b1bf3255e19, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

python-mcp-server 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 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.

AGENTS.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Estado del proyecto - Python MCP Server (iteración 3)

Contexto

Se implementaron 8 nuevas tools de análisis estático para Python, enfocadas en darle a un agente la máxima información determinista para entender un proyecto: qué hace, qué necesita, con qué interactúa, qué puede fallar, y qué está verificado.

Nuevas herramientas implementadas (src/pymcp/tools/)

#	Tool	Archivo	Estado
1	`find_entry_points`	`find_entry_points.py`	✅
2	`list_api_endpoints`	`list_api_endpoints.py`	✅
3	`extract_environment_dependencies`	`extract_environment_dependencies.py`	✅
4	`list_side_effects`	`list_side_effects.py`	✅
5	`analyze_error_handling`	`analyze_error_handling.py`	✅
6	`list_public_api`	`list_public_api.py`	✅
7	`find_test_mapping`	`find_test_mapping.py`	✅
8	`extract_domain_vocabulary`	`extract_domain_vocabulary.py`	✅

Dependencias nuevas

src/pymcp/analyzer_utils.py - utilidades compartidas (file walking, parse_module, name_from_call, etc.)

Registro

Todas las tools están registradas en src/pymcp/tools/__init__.py (r30-r37).

Problemas conocidos resueltos

libcst sin .lineno: Esta versión de libcst no expone lineno/col_offset en los nodos sin usar MetadataWrapper + PositionProvider. Se resolvió usando getattr(node, 'lineno', 0) / hasattr(node, 'lineno') en todas las referencias.
raise_counts scope: Variable definida dentro de un bloque if pero referenciada fuera. Se movió la inicialización antes del bloque.
Expressões regulares: Un raw string mal cerrado en extract_environment_dependencies.py causaba re.PatternError. Corregido.

Tests de integración

Se verificaron las 8 tools contra el código del propio pymcp (47 módulos, 18 clases, 168 funciones). Todas producen output correcto:

find_entry_points: detecta console_scripts, if __name__, apps web Typer/FastAPI/Flask, corrutinas asyncio
list_api_endpoints: detecta endpoints FastAPI/Flask/Starlette/Django con path, métodos, handler
extract_environment_dependencies: 6 regex patterns, detecta env vars, config files, Pydantic Field(env=...), load_dotenv
list_side_effects: clasifica funciones como FILE_IO, NETWORK, DB, LOG, MUTATION o PURE
analyze_error_handling: encuentra excepciones custom, raise, try/except, bare excepts
list_public_api: analiza __all__, __init__.py re-exports, top-level públicos
find_test_mapping: mapea imports de tests a módulos productivos
extract_domain_vocabulary: extrae términos del dominio y entidades clave

Read the full file on GitHub · 55 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 · 55 lines · 820 tokens per session scan A 2b1bf3255e19

Subscribe to this mod's changes

python-mcp-server AGENTS.md is an instructions file published in the GitHub repository aferreiraguido/python-mcp-server (1 stars, last pushed 12d ago), licensed MIT. It adds 820 tokens to every session, about $0.0033 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.

python-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
python-mcp-server AGENTS.mdaferreiraguido/python-mcp-server	Instructions file	1	12d ago	MIT	A	820	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

python-mcp-server: Instructions file for Codex