Code Runner Mcp

Created By
mcpc-techa year ago
Run JavaScript/Python code in a secure sandbox with support for **any package import**.
Overview

Use Cases:

  • Let AI quickly test if an npm/python package meets your requirements!
  • Use AI to run code for logic verification, reducing hallucinations!
  • Have AI write and execute testable functions for you! ...and so much more!

Core Capabilities:

  • Secure Sandbox: Code runs in an isolated environment with strict limitations on file system, network, and environment variable access, preventing malicious code from affecting the host environment.
  • Multi-language Support: Execute JavaScript/TypeScript and Python code snippets with ease!
  • Import Any Package: Dynamically import and use external libraries in your code (specific support depends on the chosen runtime).

Please note: First-time package imports require installation time, so please be patient! Subsequent runs will use cached packages, skipping the installation step. Inspired by https://ai.pydantic.dev/mcp/run-python/ project, we've reimplemented it with simplified package installation and added JavaScript support! 🚀✨ Project repository: https://github.com/mcpc-tech/mcpc/tree/main/packages/code-runner-mcp - Issues and PRs welcome!

Server Config

{
  "mcpServers": {
    "code-runner": {
      "command": "npx",
      "args": [
        "-y",
        "deno",
        "run",
        "--allow-all",
        "jsr:@mcpc/code-runner-mcp/bin"
      ],
      "env": {
        "DENO_PERMISSION_ARGS": "--allow-net"
      },
      "transportType": "stdio"
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
mcpc-tech
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago