"Exposing an MCP server via a public tunnel with mcp-proxy" matching MCP servers:

Enables ChatGPT web to read local files, search code, run shell commands, and drive a local Codex CLI via an official MCP connector, with human approval for risky commands and full audit logging.

A FastMCP-based proxy server that seamlessly integrates any MCP client with the Devin MCP API, enabling AI-powered repository analysis and question answering.

This server enables users to control and rewrite the developer instructions and MCP tool descriptions used by T3 Code's review guidance. It allows workflows to dictate the context provided to reviewers, including when to reuse existing conversations.

A local MCP bridge that lets ChatGPT chat mode operate the user's own computer, running project, file, and shell tasks through a local executor and returning progress and results to the conversation. It also coordinates Codex sessions (persistent or one-off) and other agent CLIs as sub-agents.

Delegate a Cursor task to a real, unattended background OpenCode agent — cheaper model, isolated history — through five small MCP tools.

MCP server for high-fidelity code audits, refactoring, and architectural analysis using specialized Proxy Experts.

Exposes an MCP toolset that routes each coding task to the cheapest capable model, from a free local LLM up to Claude, while giving clients file, shell, git, web, memory, knowledge-search and parallel swarm-delegation capabilities. Also allows an OpenAI-compatible REST and WebSocket API to be served for non-MCP clients.

An authenticated OpenAI-compatible inference gateway with an async job broker that bridges a coding agent to a ChatGPT MCP worker, enabling ChatGPT to process inference requests via a tunnel.

Enables MCP clients to drive local Codex on a target Git repository: inspect repo state, start and follow up on tasks, review events and diffs, and record audit evidence for research governance.

A Windows proof-of-concept MCP server that connects ChatGPT developer-mode to a local Codex CLI via Secure MCP Tunnel, exposing a small set of read-only, allowlisted tools in an isolated workspace.

A generic OpenAI-compatible subagent MCP server that lets Claude Code delegate coding grunt-work to a local model via a tool-calling agent loop, with configurable concurrency and backend.

An autonomous, extensible LLM build orchestrator. Give it a repo and a goal; it decomposes the goal into tasks, edits code, and gates every change on build/tests/lint, reverting regressions. Polygot, cost-aware model selection, pluggable via entry points. Ships as an MCP server so any client can drive it in plain English.

A stdio MCP server that lets Claude Code delegate coding tasks to an OpenCode instance (optionally attached to an internal LLM gateway), with follow-up replies, status polling, output/diff retrieval, cancellation, and cleanup handled in a single session. It supports managed or attach modes, sandbox and approval policies, parallel fan-out delegations, and read-only review workflows.

Wraps the local Qoder CLI into an MCP server, enabling any MCP client to delegate coding tasks to a local Qoder agent with session management, sandboxed permissions, and model selection.

An MCP server that connects Claude Desktop to an interactive Claude Code session running in a tmux terminal.

Enables Codex to use an installed Devin CLI as an additional worker by starting, polling, and cancelling bounded tasks through local MCP tools. It runs as a local stdio server in a given working directory, so jobs execute with the Devin account's model and permissions while Codex's own routing rules still decide when to delegate.

Self-hosted decision memory for AI coding agents. Captures decisions with the alternatives you rejected, and warns before an agent re-proposes a rejected approach.

Lets you @mention a bot in a Slack channel or DM to send work to a local Claude Code session and watch it run, with live self-updating turn cards, threaded answers, progress checklists and a per-channel inbox with read cursors. It runs entirely on your machine over Slack Socket Mode—no tunnel or public IP—routes misdelivered messages to the right project, and masks credentials in anything it posts back.

Lets AI agents create and drive Claude Code cloud sessions natively over stdio, exposing typed tools to start a session from a task description, queue follow-up messages into an existing session, and check the CLI's sign-in state. Each tool maps to a fixed Claude Code CLI invocation with strict schemas and structured JSON results, so agents never write shell commands or run local sessions.

Enables AI coding agents like Claude Code, Codex, Cursor, and OpenCode to delegate tasks to the WorkBuddy CLI as a sub-agent via an MCP tool, with one-command setup and configurable model/permission options.