mcp-code-execution AGENTS.md

Developer instructions for MCE, a Python server that lets AI discover and run API functions through a small set of tools. Its code-execution feature runs generated Python in an isolated Docker environment.

In plain words
What is it for?
Use it as the required reference when developing MCE, including its server discovery, function inspection, code execution, cached code, and reusable-code features.
Why use it?
It gives agents the project structure, fixed technology choices, quality rules, and credential-safety requirements they must follow when changing the codebase.

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/hypen-code/mcp-code-execution/agents-md
Clone the repo
git clone --depth 1 https://github.com/hypen-code/mcp-code-execution

Made for: Codex, OpenCode.

Per session 6,710 This file is loaded in full into every session.
When invoked 6,710 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.06710 $0.06710
Opus 5 $0.03355 $0.03355
Sonnet 5 $0.01342 $0.01342
Haiku 4.5 $0.00671 $0.00671

Measured yesterday against content hash 219c1c8ecffe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-code-execution AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Use `requests` or `urllib` | `httpx` only |
AGENTS.md · 619 lines

How it starts

The opening of the file, as written. The whole thing — 619 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — MCE Development Guide for AI Agents

This file governs how AI agents develop, maintain, and extend the MCE (MCP Code Execution) codebase. Read it in full before making any change.


1. Project Overview

MCE is a production-grade MCP server built with Python 3.13 and FastMCP. It exposes 4 meta-tools + 1 prompt to LLMs instead of bloating the context with N per-endpoint tools:

Tool / Prompt Purpose
list_servers Discover compiled API servers and their functions
get_functions Inspect 1–5 function signatures and return schemas (batch)
execute_code Run LLM-generated Python code in an isolated Docker sandbox
run_cached_code Re-execute a cached snippet with optional parameter overrides
reusable_code_guide (prompt) Concise rules for writing parameterized, cacheable code

Key invariant: credentials are never embedded in generated code or logs. They are injected exclusively as Docker environment variables at runtime.


2. Repository Layout

/home/ob1/aai/mcp-code-execution/      ← project root
├── pyproject.toml                      ← single source of truth for deps & tools
├── .env.example                        ← template; never commit .env
├── config/swaggers.yaml                ← swagger source definitions
├── sandbox/
│   ├── Dockerfile                      ← python:3.13-slim sandbox image
│   ├── entrypoint.py                   ← code receiver inside sandbox
│   └── requirements.txt                ← httpx, pydantic, orjson only
├── src/mce/
│   ├── __init__.py                     ← version only
│   ├── __main__.py                     ← CLI: clean | compile | serve | run
│   ├── server.py                       ← FastMCP tool registration (4 tools + 1 prompt)
│   ├── config.py                       ← MCEConfig (pydantic-settings)
│   ├── errors.py                       ← full exception hierarchy
│   ├── models/__init__.py              ← ALL pydantic models (single file)
│   ├── compiler/
│   │   ├── swagger_parser.py           ← OpenAPI 3.x / Swagger 2.0 parser
│   │   ├── codegen.py                  ← Jinja2 Python function generator
│   │   ├── orchestrator.py             ← compile pipeline coordinator
│   │   ├── llm_enhancer.py             ← optional Claude improvement pass
│   │   └── templates/function.py.j2   ← Jinja2 template for functions.py
│   ├── runtime/
│   │   ├── registry.py                 ← loads manifests, provides lookups
│   │   ├── executor.py                 ← Docker sandbox execution pipeline
│   │   └── cache.py                    ← async SQLite cache (aiosqlite)
│   ├── security/
│   │   ├── ast_guard.py                ← AST static analysis (runs before exec)
│   │   ├── policies.py                 ← read-only + domain allowlist enforcement
│   │   └── vault.py                    ← credential → Docker env var injection
│   └── utils/
│       ├── logging.py                  ← structlog setup
│       └── hashing.py                  ← SHA256 helpers for cache keys
├── tests/
│   ├── conftest.py                     ← shared fixtures (mce_config, specs, sources)
│   ├── fixtures/                       ← YAML swagger test fixtures
│   │   ├── weather_api.yaml            ← read-only, simple GET endpoints
│   │   ├── hotel_api.yaml              ← read-write, path + body params
│   │   └── petstore.yaml               ← standard petstore with $ref schemas
│   ├── unit/                           ← isolated, no Docker, no network
│   │   ├── test_swagger_parser.py
│   │   ├── test_codegen.py
│   │   ├── test_ast_guard.py
│   │   └── test_cache.py
│   └── integration/                    ← requires compiled output on disk
│       └── test_compiler.py

Read the full file on GitHub · 619 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 · 619 lines · 6,710 tokens per session scan A 219c1c8ecffe

Subscribe to this mod's changes

mcp-code-execution AGENTS.md is an instructions file published in the GitHub repository hypen-code/mcp-code-execution (10 stars, last pushed 4mo ago), licensed MIT. It adds 6,710 tokens to every session, about $0.0335 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens