Code Executor Mcp

Name: Code Executor Mcp
Author: CSOAI-ORG

CSOAI-ORG/code-executor-mcp

Updated July 25, 2026
CSOAI-ORG/code-executor-mcp

code-executor-mcp is a MCP server that executes agent-submitted code via stdio and returns run output for fast validation during implementation.

About

code-executor-mcp is a Model Context Protocol server from MEOK AI Labs that gives developers a controlled way to execute code from inside AI coding agents. Instead of switching terminals to sanity-check a snippet your agent just wrote, you register this stdio server (PyPI identifier code-executor-mcp) and expose execution as a tool the model can invoke. That pattern matters when you ship fast with Claude Code, Cursor, or Codex: you catch syntax errors, wrong assumptions, and bad imports before they land in your repo. The catalog lists it under Build → agent-tooling because it is an integration layer, not a full test harness or deploy pipeline. Pair it with review-oriented MCPs when you want run-then-critique loops. Expect to treat execution as privileged: scope what the agent can run and which environments you trust, especially on your main machine.

PyPI package code-executor-mcp v1.0.4 with stdio MCP transport
Runs agent-supplied code and returns structured execution results
Supports quick validation loops for generated backends and CLI utilities
GitHub-hosted under CSOAI-ORG / MEOK AI Labs for version pinning
Fits agent-first workflows where copy-paste manual runs slow you down

Code Executor Mcp by the numbers

Data as of Jul 26, 2026 (Skillselion catalog sync)

terminal

claude mcp add code-executor-mcp -- uvx code-executor-mcp

Add your badge

Show developers this MCP server is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/mcp/tool/io.github.CSOAI-ORG/code-executor-mcp.svg)](https://skillselion.com/mcp/tool/io.github.CSOAI-ORG/code-executor-mcp)

Package	code-executor-mcp
Transport	STDIO
Auth	None
Last updated	July 25, 2026
Repository	CSOAI-ORG/code-executor-mcp ↗

What it does

Let your coding agent run Python or shell snippets in a sandbox and return stdout, errors, and exit codes without leaving the chat.

Who is it for?

Best when you use agent-heavy stacks and want immediate run feedback on Python or shell snippets while prototyping APIs, CLIs, and automation.

Skip if: Skip if you need hardened multi-tenant sandboxes, full CI matrices, or production job orchestration without additional guardrails beyond this MCP.

What you get

Your agent can run snippets on demand so you confirm behavior, fix failures, and iterate in one workflow instead of manual copy-paste runs.

Registered stdio MCP server the agent can call for code runs
Structured stdout, stderr, and exit status returned into the agent thread
Faster validate-fix cycles on small scripts before git commit

By the numbers

Server schema version 1.0.4
Single PyPI package with stdio transport
Repository: github.com/CSOAI-ORG/code-executor-mcp

README.md

Code Executor MCP

Sandboxed code execution: Python, JavaScript, and shell commands with safety guards, output captu...

Sandboxed code execution: Python, JavaScript, and shell commands with safety guards, output capture, and timeout protection.

Quick Install

Client	Install
Claude Desktop
Cursor
VS Code
Windsurf
Docker	`docker run -p 8000:8000 code-executor-mcp`
pip	`pip install code-executor-mcp`

Overview

🚀 Quick Start

# Install via pip
pip install code_executor_mcp

# Or install via Smithery
npx -y @smithery/cli@latest install code-executor-mcp --client claude

✨ Features

MCP protocol compliant
Easy installation
Well-documented API
Production-ready
Active maintenance

📖 Documentation

🛡️ Compliance

This MCP server is built with EU AI Act compliance built-in:

✅ Article 9 — Risk Management System
✅ Article 13 — Transparency & Instructions for Use
✅ Article 15 — Bias Detection & Testing
✅ Article 26 — FRIA Support (where applicable)
✅ Article 50 — AI Content Watermarking (where applicable)

Need help getting compliant? Book a free 15-min diagnostic →

🏢 Enterprise

Need custom development, SLA guarantees, or white-label deployment?

Pro: $99/mo — Full MCP suite + EU AI Act tracking
Enterprise: $499/mo — Custom dev + SLA + Dedicated support

View Pricing → | Contact Sales →

🤝 Part of the MEOK Ecosystem

This server is part of the MEOK AI Labs ecosystem — 300+ MCP servers for sovereign AI governance.

Domain	Purpose
councilof.ai	EU AI Act compliance marketplace
safetyof.ai	AI safety & monitoring
meok.ai	Sovereign AI platform
cobolbridge.ai	Legacy modernization

📜 License

MIT © CSOAI-ORG

_{Built with 💜 by MEOK AI Labs · UK Companies House 16939677}

MIT © [MEOK AI Labs](https://meok.ai)

Pairs with MEOK Governance Suite

Build something that touches users? You need compliance. MEOK ships 38 governance MCPs that drop in alongside this tool — EU AI Act, DORA, NIS2, CRA, GDPR, ISO 42001, FDA SaMD, MDR, Basel, MiFID II, MiCA, COPPA, and more.

# One-shot install of the governance pack
npx meok-setup --pack governance

Free tier: 10 calls/day per MCP. Pro tier (£79/mo): unlimited + cryptographically signed compliance attestations your auditor verifies independently.

→ Full catalogue: councilof.ai/catalogue → MEOK AI Labs: meok.ai

💸 Try MEOK in 30 seconds — instant buy ladder

Tier	Price	What you get	Stripe
Smoke test	£1	Signed sample MCP-Hardening report + Article 50 PDF	https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t
Quick Kit	£9	EU AI Act Article 50 implementation guide (C2PA + EU-Icon)	https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t
Founder Call	£29	30-min 1-on-1 with the founder	https://buy.stripe.com/aFa7sNcgAdQS0ZT1Uc8k91t

Refundable. UK Stripe — VAT-clean. Builds on the 81-MCP MEOK fleet. Verify any signed report at https://meok.ai/verify.

Configuration

Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:

{
  "mcpServers": {
    "code-executor-mcp": {
      "command": "uvx",
      "args": ["code-executor-mcp"]
    }
  }
}

Or: pip install code-executor-mcp then run the code-executor-mcp command (stdio transport).

Examples

Once configured, ask your assistant, for example:

"Use execute_code to …"
"Use run_command to …"
"Use run_tests to …"

Recommended MCP Servers

0piFree, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data.

100Hires AI ATS & Recruitment SoftwareOfficial 100Hires MCP: AI ATS & Recruitment Software for candidates, jobs, applications, interviews.

123elec McpInterface MCP officielle du site marchand 123elec, catalogue, stock, panier, commandes.

1stayHotel booking MCP server.2

2D Assets MCPMCP server for generating advanced mock 2D PNG assets for game prototypes.4

3D MeshWeaverMesh spatial optimizer reducing geometric overhead in 3D assets.

How it compares

MCP execution bridge, not a hosted notebook platform or a full CI/CD runner.

FAQ

Who is code-executor-mcp for?

Developers who use Claude Code, Cursor, or similar agents and want run-output tools wired through MCP instead of manual terminal steps.

When should I use code-executor-mcp?

Use it during Build when you are validating agent-generated code, debugging small scripts, or closing the loop before you commit larger changes.

How do I add code-executor-mcp to my agent?

Install the PyPI package code-executor-mcp (v1.0.4), add a stdio MCP server entry pointing at that package, restart your agent, and confirm the execution tool appears in the tool list.

Developer Toolsbackendtestingintegrations