"Developing agents with expertise in the latest documentation" matching MCP servers:

Persistent memory and pattern learning for AI coding assistants via MCP.

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.

Enables ChatGPT to drive sandboxed coding tasks via the Agents API, with independent review and exact-tree draft pull request publication for allowlisted repositories.

A transport-agnostic MCP server that integrates multiple AI coding agents (Claude Code, Gemini, and Codex) with built-in tools for command execution, calculations, and streaming capabilities. Supports both STDIO and HTTP transports for flexible deployment.

MCP server that wraps AI CLI tools — Claude Code, Antigravity CLI, and Codex CLI — so any MCP client can call them as tools.

Enables Codex to delegate code reviews, coding tasks, image/video generation, and background investigations to Grok via MCP tools.

Lets MCP-compatible clients run reusable Markdown-defined coding agents with a chosen backend CLI and return their results to the same conversation. It supports delegating tasks such as code review, test writing, investigation, and documentation, with shared settings and optional session continuation.

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.

Enables defining reusable, task-specific coding agents in Markdown and running them from any MCP-compatible client through a chosen coding CLI. Supports delegated code review, test writing, investigation, and documentation, with shared backend/model configuration, permission modes, and sessions that continue work across multiple calls.

Enables AI assistants and other MCP clients to launch and steer Cursor Cloud Agents on repositories or as repo-less research tasks, including model selection, mid-run follow-ups, cancellation, result retrieval, and run listing. Also exposes authentication checks and per-agent or per-run token usage and cost reporting.

Enables an orchestrator like Claude Code to hand coding work off to Cursor SDK agents, run as detached background jobs that survive the session and can be listed, inspected, steered, resumed, or stopped. Agents are asynchronous and reusable across follow-up turns, letting expensive frontier models delegate cheaply without blocking or paying to read the results.

Enables AI assistants and MCP clients to launch and manage Cursor Cloud Agents on repositories or without one, select models, follow up mid-run, retrieve or cancel results, and check usage and cost.

Routes work from your coding agent across 20+ free-tier LLMs to cut costs 10-100x using a round-robin dispatch pool with cooldown-aware auto-fallback.

Enables Claude Code to delegate tasks to OpenAI's Codex CLI (GPT-5.4) with structured execution traces, parallel execution, session persistence, and adversarial code review.

Enables orchestrating multiple AI CLI agents (Claude Code, Codex, Gemini CLI, Copilot CLI) through a unified MCP interface for task delegation, cross-agent comparison, and specialized tools like code review and debugging.

Enables AI coding tools to call Grok and Antigravity CLIs as peer reviewers for code review, planning, debugging, and collaborative sessions.

Enables delegating coding tasks to multiple AI CLI agents (Claude Code, Antigravity, Codex, Cursor) with session memory and diff inspection.

Enables MCP-compatible clients to run reusable, task-specific coding agents defined in Markdown files, executing them through a chosen coding CLI backend and returning results to the same conversation. Supports shared agent, model, and permission configuration plus session continuation across multiple calls.

Enables users to run reusable Markdown-defined coding agents from any MCP-compatible client, delegating tasks such as code review, test writing, investigation, and documentation to a chosen coding CLI backend and returning results to the same conversation.

Enables users to define reusable task-specific agents in Markdown and run them through any MCP-compatible client using a chosen coding CLI backend, returning results to the same conversation. Supports shared backend/model configuration, permission modes, and optional cross-call session continuation.