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.
MCP server that parses .sketch design files into CSS-aligned, LLM-friendly JSON, enabling AI coding agents to generate high-fidelity HTML, Vue, or React code.
MCP server that lets you drive Claude Code sessions hands-free by voice from any MCP client, enabling remote models to send prompts, monitor progress, and get results read back.
Connects ChatGPT to Roblox Studio's built-in MCP, enabling natural-language reading and writing of game data, including executing Luau code and modifying scripts and instances.
A task-level STDIO MCP server that lets Codex or any other MCP client hand off scoped coding jobs to an asynchronous worker agent which reads the code, edits files, and runs tests, while the client keeps ownership of planning and acceptance. Exposes submit, wait, query, follow-up, and cancel tools so multiple clients can queue and monitor tasks against a chosen project root.
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.
Enables two-model orchestration where Gemini in Google Antigravity delegates coding tasks to Qwen 3.8 Max in Qwen Studio Desktop via CDP, managing prompt delivery, file generation, continuation, and verification.
Bridges Claude Desktop with Claude Code CLI to delegate complex coding tasks like creating React apps, building APIs, and debugging scripts while maintaining interaction through the Desktop interface.
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 running one Codex CLI task at a time in an isolated temporary folder, returning Codex's answer and a manifest of produced files for manual review and selective copying.
Enables Claude Code to use GLM (Zhipu) as a cheap, full-capability subagent for file editing, code generation, and bash commands, with automatic routing between Opus and GLM based on task complexity.
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 remote control of AI coding assistants (Claude Code/Codex) via Telegram, allowing you to manage long-running tasks, send commands, and receive notifications from anywhere. Supports unattended mode with smart polling for up to 7 days and multi-session management.
Lets Claude Code delegate bounded coding tasks to a GLM model as a sub-agent through a single MCP tool that reads, writes, edits, lists directories, and runs shell commands inside a specified project folder. Each run returns only a short report with changed files and token usage, keeping GLM's intermediate tool traffic out of Claude's context.
Tells coding agents what changed in a Python library, in which release, and what replaces it. Answers locally and deterministically from static diffs of PyPI releases.
Enables Windows users to connect Antigravity CLI as an MCP subagent for coding tasks such as file reading, code execution, edits, and terminal commands, with model selection, conversation continuity, and streaming progress.
Gives any MCP client the same sandboxed coding-agent toolset — searching, viewing and editing files, running tests, and executing shell commands — each session in its own locked-down, network-isolated Docker container. Enables an MCP-capable assistant to diagnose and fix failing tests without touching the host machine.
Enables handing one self-contained job to the Claude Code CLI on the local machine and getting back its final message plus a manifest of the artifacts it produced, without letting Claude write into the user's project. Reads are limited to named directories and all writes stay in a throwaway run directory, so the user reviews the listed files and copies in only what they approve.
Drive Elixir terminal UIs headlessly from an agent: start a TUI session, send keystrokes, take structured screenshots, and read TEA model state as MCP resources. Also exposes adaptive-UI recommendation tools and, when raxol_agent is loaded, read-only coding-agent session tools.
Enables coding agents to verify completion locally against a declared spec by checking changed files, produced outputs, recomputed records and totals, and only approved commands, then blocking the stop with structured fixes and replayable evidence. It uses deterministic rules only, with no model calls, network access, or dependencies.
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 MCP leaders such as Claude Code, Codex, ChatGPT, and Claude Desktop to delegate long-running coding and execution work to a local DSH backend, including reading code, editing files, running commands and tests, and retrieving asynchronous results with approval, sandboxing, and task-management controls.
GhostLink is a security-hardened MCP server that gives AI coding agents safe, deterministic access to local repositories through sandboxed, policy-gated tools for searching, reading, patching, and running curated commands.
Provides coding agents with repository context through tools that generate AGENTS.md files or structured JSON summaries, quoting build/test commands from the repo's manifests for a small fee without an API key.
Turns a Claude Desktop or Claude Code conversation into an orchestrator for parallel AI coding agents, each running in its own Tern terminal tab and git worktree on its own branch, with any model available on the machine. It enables starting, monitoring, correcting, and merging agents—reading their reports and diffs, switching models or thinking levels mid-task, and enforcing model policies.
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 an MCP client such as Codex to delegate bounded development tasks to a separate DSH agent harness, track progress, and inspect model-reported results alongside independently recorded SDK events, workspace changes, and optional verification commands. It also lets the client explicitly review, continue, or cancel a live delegated run rather than accepting a returned report automatically.
MCP server that delegates bounded coding tasks to a server-side agent loop, persisting task state and conversations in SQLite while restricting file and command operations to a guarded workspace.
Enables coding agents to inspect and mutate code in zero-copy RAM shadow workspaces, explore competing fixes in parallel, and commit only syntax- and test-validated changes to disk through a compact MCP tool surface.
A fully featured coding agent that uses symbolic operations (enabled by language servers) and works well even in large code bases. Essentially a free to use alternative to Cursor and Windsurf Agents, Cline, Roo Code and others.
Exposes the Mavis multi-agent system as an MCP server, enabling Claude Code and other MCP clients to manage sessions, spawn agents, orchestrate team tasks, and perform code reviews, memory searches, and cron scheduling via natural language.
Enables AI agents to orchestrate tasks as a DAG with automated validation loops, executing validation commands, tracking statuses, and allowing iterative code fixes until tasks pass.
Delegates test writing to a headless second coding agent in an isolated git worktree, then builds, runs the tests, verifies that only test paths changed, and returns a compact report plus optionally applies the verified tests to your checkout. It also flags failures that point to bugs in the production code rather than the tests, keeping test code and terminal logs out of the main agent's context.
Enables MCP clients to run Cline CLI prompts and isolated repository-wide analyses, returning terminal text responses with model, duration, and usage/cost.
Enables MCP clients to start and steer persistent terminals and coding agents, run commands and edit files on local or remote machines, and arrange the Herdr desktop window.
Bridges a main agent (e.g., Codex) to a separate execution model in Claude Code Haha Desktop, enabling delegated coding tasks with file modifications, test runs, and change auditing.
Enables any MCP client to read, search, patch, and execute commands in a codebase, including interactive sessions and git operations, with permission modes and safety boundaries.
Enables Claude Code to delegate tasks such as planning, coding, reviews, debugging, tests, and docs to a cheaper model that works autonomously in a project-sandboxed loop with file, search, and test tools, returning a compact report to save tokens. Routing rules, approval-gated deletes and commands, per-task model/effort settings, and backups keep the user in control of what gets handed off.
Enables non-coders to build software by describing ideas in natural language, orchestrating AI agents and CLI workers via chat without needing a terminal.
Lets MCP-capable AI agents drive Orca through its official CLI: creating git worktrees, launching coding agents like Claude or Codex, sending input to and reading terminal output, and tracking orchestration tasks and messages. It also exposes status, search, and automation tools with strict input validation and safe, non-destructive defaults.
Enables AI agents with an always-on computer to orchestrate Kiro CLI V3 coding sessions through typed tools rather than shell commands. Exposes 32 tools plus a subscribable transcript resource for creating, configuring, prompting, steering, forking, and exporting sessions, with operator-policy gating and bounded process control.
Enables any MCP client to start, inspect, wait for, and communicate with fleets of coding agents in worktrees, with structured status, completion events, orchestration mail, and terminal control.
Persistent, local memory for AI coding agents that learns how you work, not just what you said. Supports Claude Code, Codex CLI, Cursor, and any MCP client.
Integrates the Atlassian Rovo Dev CLI with the Model Context Protocol, allowing AI assistants to perform deep code analysis using Rovo Dev's large context capabilities. It enables features like repository-wide queries, file-specific analysis, and specialized coding modes through a standard MCP interface.