"How to work with local files" matching MCP servers:

Enables MCP-compatible AI clients to securely access explicitly authorized local project files and run approved development commands with bounded execution and audit logging.

A minimal MCP server that exposes a run_command tool over stdio, enabling command execution within a Docker container.

Enables supervised PowerShell execution on Windows, allowing the DeepSeek agent to run local commands and manage files safely through a single tool.

Local MCP server that registers restricted Python filters and runs them against local JSON, YAML, and TXT files, enabling safe data filtering and file conversion.

Exposes the Grok Build CLI as MCP tools for Claude Code and other clients, enabling headless AI agents to perform tasks like code reviews, web research, and file operations with configurable permission levels.

An MCP server that offloads bulk coding tasks to local LLMs, allowing Claude Code to delegate repetitive work like boilerplate generation and code polishing while preserving its context for complex reasoning.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables any LLM to drive your local Codex CLI in a sandboxed workspace, running coding tasks and generating images without needing an API key.

Enables AI assistants to read, edit, and execute Jupyter notebook files (.ipynb) with live kernel output, without requiring JupyterLab.

A local development MCP server that exposes MySQL databases to VSCode and Copilot CLI with read-only SELECT queries and INSERT/UPDATE operations. It provides secure, schema-specific database access for development environments only.

An MCP server that lets host-side Claude Cowork dispatch work into Claude Code running inside your devcontainer over stdio.

Stdio MCP Server wrapping custom Python runtime (LocalPythonExecutor) from Hugging Faces' smolagents framework. The runtime combines the ease of setup (compared to docker, VM, cloud runtimes) while providing safeguards and limiting operations/imports that are allowed inside the runtime.

Enables an AI agent to make music with SuperCollider by rendering code to WAV files offline with peak and RMS level stats, plus realtime playback and stopping. Runs on macOS and Linux via a subprocess, with per-call process isolation so crashes or hangs can't take the server down.

Enables Claude Code to work with personal data that stays on the local machine, running SQL, Python, and file/schema inspection in a sandboxed compute-to-data setup that returns only aggregates, schemas, synthetic fixtures, and pseudonymized results. Raw records, file names, and protected values never reach the Anthropic API, so Auto mode can stay hands-off.

Enables agents to run constrained optimization loops on local source files, using Step-5-Preview to propose changes while measuring candidates and returning verified patches.

Enables ChatGPT Developer Mode to operate as a local coding agent by connecting to your own repository through MCP, allowing it to read, write, search, edit files, run safe verification commands, and manage handoff context for continued work.

Enables ChatGPT web to interact with local Windows/WSL shell and code workspaces via an MCP server, providing file access, shell execution, and snapshot-based workspace management with per-command authorization.

A demonstration server that reveals security risks by accessing sensitive environment variables, illustrating how MCP tools can potentially leak user data without explicit consent.

Connects AI agents to microsandbox for creating lightweight sandboxes, executing code, managing files, and monitoring resources.

Shell and file edit capabilities tightly coupled to provide a powerful coding experience. You can work with different modes: architect and code-writer for separate plan and implementation phase. You can get it to invoke any cli command, e.g., compiling, type checking, linting, github cli, python

Enables creating, inspecting, and stopping Google Colab sessions, executing Python code or files, retrieving session URLs, and reading logs through the local Colab CLI.

Enhanced fork of Google's Colab MCP, pre-registers all 7 notebook tools at startup (get_cells, add/run/update/delete/move_cell, add_text_cell), adds programmatic GPU control (T4/L4/A100) via OAuth, and fixes the "Disconnected from local server" issue with IPv4-only bind, PNA CORS headers, and stale-tab dedup. Works on Chrome, Edge, Windows, macOS, Linux.

A comprehensive MCP server providing tools for AI agents to interact with code, including reading symbols, importing modules, replacing text, and sending OS notifications.

Enables LLMs to interact with Python environments, execute code, manage files, and handle packages through the Model Context Protocol.

A multi-agent collaborative development bridge that enables TRAE Work to offload complex tasks to Codex executor, with tools for task submission, status tracking, artifact listing, and permission management.

Gives an LLM a secure local workspace where it can write files, execute Python in a locked-down Docker container with no network access, and run read-only SQLite queries. Lets the model run, debug, and fix its own code without risking the host machine.

Build agent skills where you work — write a script, add a SKILL.md, and use it in Claude Code/codex/Cursor immediately. The same fixed entry point that runs locally deploys to production without a rewrite.

MCP Server for the Peacock extension for VS Code (https://peacockcode.dev), coloring your world, one Code editor at a time. The main goal of the project is to show how an MCP server can be used to interact with APIs.

Bridges a local agent to a Colab session in the browser, enabling seamless interaction with Colab from local clients.

Automatically provides AI assistants with contextual, version-specific documentation for Python project dependencies by scanning pyproject.toml files. Eliminates manual package lookup and enables more accurate coding assistance through seamless integration with AI tools.