Python Runner MCP Server

Created By
taiji1985a year ago
A MCP Server Of python runner
Overview

What is Python Runner MCP Server?

Python Runner MCP Server is a Python code execution server based on the FastMCP framework, designed specifically for data science and machine learning workflows.

How to use Python Runner MCP Server?

To use the server, you can run it directly using the uvx command or configure it in the Claude Desktop application. You can also make direct API calls to execute Python code.

Key features of Python Runner MCP Server?

  • Safe Python code execution in isolated namespaces.
  • Pre-installed with popular data science and machine learning libraries.
  • Real-time output capture for standard and error outputs.
  • Fully compatible with Model Context Protocol (MCP).
  • Simple and clean API interface for ease of use.

Use cases of Python Runner MCP Server?

  1. Executing Python code for data analysis and visualization.
  2. Running machine learning models and evaluating their performance.
  3. Integrating with applications like Claude Desktop for seamless code execution.

FAQ from Python Runner MCP Server?

  • Can I run any Python code?

Yes, you can execute arbitrary Python code, but ensure it is done in a trusted environment due to security considerations.

  • What libraries are pre-installed?

The server comes with libraries like numpy, pandas, scikit-learn, matplotlib, and more for data science tasks.

  • Is there a way to debug the server?

Yes, you can use the MCP Inspector to debug the server.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
taiji1985
Star
0
Language
Python
License
-

Recommend Servers

View All
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