"A lightweight, self-hosted Git service" matching MCP servers:

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.

AI code review against your team's own rules from your repository, before the pull request: two tools, review_changes and get_team_rules. Closed-source binary distributed via GitHub Releases; published in the official MCP Registry as dev.reviewgate/reviewgate.

An MCP server for running Claude Code and the Codex CLI as a pair: Claude drives, and hands self-contained tasks to Codex as background jobs.

An enhanced sequential thinking tool optimized for programming tasks that helps break down complex coding problems into structured, self-auditing thought steps with branching and revision capabilities.

Enables multiple AI agents to collaborate on the same git repository by coordinating work via a shared claims branch, detecting file conflicts before they happen.

Adds guardrails around delegating tasks to OpenAI Codex, including quota preflight and handoffs, git worktree isolation, per-turn checkpoints and restore, read-only cross-reviews, and honest failure reporting.

Provides AI coding agents with five intelligence layers (dependency graph, git history, documentation, architectural decisions, code health) via nine MCP tools, enabling deep codebase understanding and reducing exploration cost.

Enables MCP clients to delegate routine coding tasks to a local model in isolated git worktrees, using test results as a gate and the client as the reviewer before changes are merged.

Delegate coding tasks to external AI coding agents in isolated git worktrees with independent verification, enabling any MCP client to orchestrate multi-agent workflows.

A local stdio MCP service that unifies coding agents like Codex and Claude into cs_agent_* tools, enabling the root agent to create, invoke, and manage child agents with recursive delegation.

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.

Enables delegating complete coding tasks to a local OpenAI-compatible model through MCP, using bounded Git worktrees and compact receipts so conversation history is not carried.

Enables primary AI orchestrators to delegate token-heavy coding tasks to economical models via OpenRouter, running sandboxed autonomous ReAct loops with filesystem operations and git audit tools while reducing token costs.

A TypeScript MCP server that lets AI assistants interact with the Godot 4.x game engine: not just editing files, but playing the game.

Enables multiple AI agents to coordinate work on the same codebase by providing real-time file locking, commit approval, and agent awareness through a lightweight WebSocket-based MCP server.

A stdio MCP server that lets Codex Desktop/CLI delegate implementation tasks to Claude Code CLI with workspace validation, Git status checks, and session resume capabilities.

Enables Codex to delegate coding tasks to an OpenCode CLI locally, returning structured results such as exit codes, session summaries, tool calls, and git diffs.

MCP server for Codex CLI — tmux persistence, git worktree isolation, async dispatch.

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.

Enables Claude Code to run cursor-agent tasks in isolated git worktrees, manage asynchronous and parallel jobs, review diffs, and safely apply changes back to the repository.