Local Terminal MCP — Development skill for Claude Code
Run local commands from ChatGPT or Claude via a safe, allowlisted MCP server.
How to install Local Terminal MCP
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open luckysolanki902/local-terminal-mcp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Local Terminal MCP does
Run local commands from ChatGPT or Claude via a safe, allowlisted MCP server. Work on your codebase and generate images/sprites/assets locally from ChatGPT without spending Codex/API tokens. stdio for Claude Desktop/Code; capability-URL or bearer auth over HTTP for ChatGPT via ngrok or cloudflared.
Alternatives in Development
- Code Review Graph — Local knowledge graph for Claude Code 3.7k ★
- MCP Proxy — A bridge between Streamable HTTP and stdio MCP transports 2.4k ★
- Obsidian MCP Server — Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP 686 ★
README
local-terminal-mcp
A small, security-first [MCP](https://modelcontextprotocol.io) server that lets an AI assistant — **ChatGPT**, **Claude Desktop**, **Claude Code**, or any other MCP client — run a set of **allowlisted** commands and read files from a local directory on your machine.
The motivating use case: point ChatGPT (or Claude) at a local codebase so it can run `git`, `rg`, `cat`, etc. and analyse the repo — without copying files around by hand, and, for ChatGPT, using your flat-rate subscription instead of metered API/agent tokens.
⚠️ **This runs commands on your computer.** It is built to be safe by default (read-only, allowlisted, no shell, path-contained, auth-required over the network), but you are responsible for how you configure and expose it. Read [Security model](#security-model) before exposing it to the internet.
Table of contents
- Why this exists
- How it works
- Security model
- Install
- Quick start (local / stdio)
- Connect to Claude Desktop
- Connect to Claude Code
- Connect to ChatGPT (over the internet) · exact step-by-step guide
- Configuration reference
- Tools exposed
- Development
- FAQ
Why this exists
Running a coding agent against a large repo through a metered API burns tokens fast. If you already pay for a ChatGPT or Claude subscription, you can instead give the assistant a *tool* to read files and run read-only commands on your machine, and let it analyse the code conversationally. That is what this server provides, with a security model strong enough that you can leave write access turned off and expose only read access.
What you can do with it
- **Work on your codebase from ChatGPT without spending Codex/AP
Related Skills
Pvc Img Gen Codex
Claude Code skill that makes and edits real images through the Codex CLI from the OpenAI ChatGPT VS Code exten
Forgeflow Compact Output
Compact allowlisted noisy command output without touching correctness-critical output.
Aura Components MCP
Free MCP for Aura's public catalogue: 2,495 components, 187 skills, 30k assets. No login, no key, one stdio ca
Fables
Four Claude Code / Codex plugins for spending tokens where they change the outcome
Generate Image Skill
Give your coding agent the power to generate its own images locally with FLUX.1-schnell — free, offline, no AP
Generate Assets
Generate real game assets — images, textures, skyboxes, 3D models, SFX, music, voice, and intro/cinematic vide
Related Agents
ChatGPT Reviewer
Use when the main thread wants a second opinion on a change from ChatGPT without spending its own context read
Image Generator
Generates and edits images using the OpenAI Image API via the bundled CLI (scripts/image_gen.py). Use for conc
2D Artist
Owns 2D art pipeline quality — sprites, tilemaps, 2D animations, UI visual assets, and placeholder assets.