"How to run a Python script in a sandboxed environment" matching MCP servers:

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Local MCP server for A-share stock trading via Tonghuashun, offering account/position queries, buy/sell/cancel orders with risk controls and forced user confirmation; currently simulated with a reserved interface for real broker channels.

A-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.

An MCP server for searching and downloading books from Library Genesis, supporting EPUB, MOBI, PDF, and more through natural language queries.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

MCP server adapter that exposes A-share stock data tools, prompts, and resources via FastMCP, enabling querying of stocks, K-lines, financials, sectors, and market hot spots through natural language.

MCP server that provides tools to access Google Maps Environment APIs for air quality, pollen, and weather data, enabling queries like current conditions, forecasts, and history.

Enables AI-to-AI consultation for critical thinking and complex reasoning via OpenRouter, allowing one AI to delegate tasks to another AI model.

Executes IDAPython scripts in IDA Pro through any MCP-compatible AI assistant, enabling AI-powered binary analysis with full access to IDA's API.

Enables AI clients to connect locally over stdio, discover and read schemas for native page tools, and execute user-authorized operations supplied by websites and independent user scripts.

Production-ready MCP server providing RAG, hierarchical memory, and 8+ tools for AI agents via the Model Context Protocol.

Enables you to audit your AI agent skills by running each one against an agent that cannot see it, diffing the resulting artifacts, and grading whether each skill genuinely improves, changes nothing, or worsens the output.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

Enables execution, listing, reading, and help retrieval of local Bash, PowerShell, and Python scripts from a specified directory.

Enables users to query Chinese A-share stock data, including stock basics, historical prices, financial reports, and macroeconomic indicators.

Enables execution of arbitrary CLI tools and shell scripts by defining them in YAML configuration files as MCP Tools. Supports custom shells (bash, Python, Node.js, Deno), input parameters passed as environment variables, and flexible timeout settings.

Call OpenAI Codex from Claude Code for independent second opinions, structured code review, and delegated coding tasks through a FastMCP plugin that drives the codex CLI safely.

Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

Provides MCP tools to disassemble Kaspa scripts, estimate compute costs, explain txscript errors, and look up opcodes.