Code Executor MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/csoai-org-code-executor-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

3 read · 1 write · 3 delete

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Python package

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• execute_code

  Execute code in a sandboxed environment with safety checks. Supported languages: python, javascript. Timeout: max 60 seconds (30 default). Dangerous patterns (os.system, subprocess, eval(input), etc.) are blocked. Output is captured and returned (stdout + stderr, truncated at 10KB). Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. W…

• execute_code_docker

  Execute code inside a temporary Docker container for isolation.

• get_safety_rules

  Get the current safety rules and blocked patterns for code execution. Useful for understanding what is and isn't allowed. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: …

• list_sandbox_files

  List files in the sandbox working directory. All code execution artifacts are stored here temporarily. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or standards. When NOT to use: Not suitable for r…

• read_file

  Read contents of a file (restricted to allowed directories: Desktop, Documents, Downloads, /tmp, and the sandbox). Returns file content with line limit. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against established frameworks or s…

• run_command

  Execute a shell command and return stdout/stderr/exit_code. Timeout: max 60 seconds. Destructive commands (rm -rf /, dd, fork bombs, pipe-to-shell) are blocked. Commands run in a temporary sandbox directory. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classific…

• run_tests

  Run a test suite and return results. Default: pytest. Specify working_dir to run tests in a specific project directory. Returns stdout, stderr, exit code, and pass/fail summary. Behavior: This tool is read-only and stateless — it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage. When to use: Use this tool when you need structured analysis or classification of inputs against es…

Signals

Stars

0

Forks

0

Open issues

0

Weekly downloads

57

Last commit

Sep 4, 2026 (1 month ago)

Last release

Jun 30, 2026 (4 months ago)

Last package publish

Jun 27, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.CSOAI-ORG/code-executor-mcp

Version

1.0.12

Auth

No auth

Packages

pypi code-executor-mcp

License

MIT

Repository

github.com/CSOAI-ORG/code-executor-mcp

First seen

Oct 24, 2026

Last checked

Oct 25, 2026

Source

Official MCP Registrygithub-graphql