"Creating the Best General-Purpose Agent" matching MCP servers:

Enables code execution in isolated Docker containers with persistent IPython, Node.js, or R kernels, supporting file import/export and cross-session transfers via MCP tools.

Provides per-Subagent MCP controls to any coding agent or client across all your MCPs and prevents context window waste. Loads only 3 tools instead of all your MCP Server's tool definitions. Agents discover tools on-demand, only when needed and only the servers and tools they are allowed.

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.

Delegates coding and read-only exploration tasks to the Antigravity CLI as blocking headless runs, mirroring live progress to on-disk stream transcripts and diffing git status to report touched files and out-of-scope edits. Supports resumable conversations, per-call model/agent/effort overrides, idle and hard timeouts, and discovery of available models and agent profiles.

Agent NERO is an MCP server that enables Claude Code to spawn, manage, and communicate with persistent, named LLM agents that maintain conversation history and can use tools like file I/O, command execution, and shared memory.

Enables MCP hosts such as Codex or Claude Code to delegate work to Cursor Agent and continue the same Cursor session until the requested work is done.

MCP server for bidirectional AI agent collaboration — 5 tools for spawning and communicating with any agent CLI

Routes multiple ChatGPT chats to allowlisted Git workspaces through a single MCP endpoint, and manages persistent Pi and Codex agent pools for coordinated, checkpointed work.

Unified MCP interface to monitor and control coding agents across OpenCode, Claude Code, and Codex CLI.

Shared knowledge graph for AI coding agents. Search, create, and link verified technical knowledge across 12 node types with trust scoring, demand signals, and auto-provisioning. Install: npx agent-hive-mcp

MCP server that spawns autonomous Claude Code agents in GitHub repos, enabling task delegation with persistent state, multi-step workflows, and job monitoring.

Enables AI coding agents to review Swift code, scaffold new iOS apps, and build, test, and preview them in the Xcode Simulator using local Apple guides and source references.

Enables coding harnesses such as Claude Code, opencode, and Codex to hand tasks off to Perch AI as an autonomous worker and receive structured results with thread ids, model identity, and token usage. Supports asynchronous job tracking, thread continuation, and cancellation of long-running delegations.

Lets orchestrators like Claude Code and opencode hand off coding tasks to an autonomous Perch AI worker that does the work and returns verifiable evidence. Supports async job handoff with status polling and cancellation, thread continuation, model pinning, and built-in discipline guidelines for minimal, verified changes.

Service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents via MCP. Versioned Markdown store, pub-sub notifications, and diff-aware update protocol.

A fast, hardened MCP server that lets any MCP host drive the Cursor Agent CLI for heavy repo-aware tasks like search, analysis, planning, and edits, keeping host context small and token costs low.

Enables external AI clients to invoke an autonomous coding agent that plans, fixes, and self-corrects code in an isolated Docker sandbox via run_task and run_tests tools.

An MCP server that wraps the Claude Agent SDK, enabling Claude-powered queries, coding tasks, web search, and customizable agent execution using OAuth without an API key.

A zero-dependency MCP server that allows multiple coding agents to coordinate work on the same repository using file locks, task claims, and status messages.

Enables MCP clients such as Claude Code and Codex to delegate persistent review or isolated write-mode implementation tasks to locally installed Claude Code or Codex runtimes, then inspect progress, approve or deny individual permission requests, and continue the same native conversation. It also lists live model catalogues, lets callers follow up on saved conversations, and can run independently via its bundled CLI.

Shared troubleshooting memory and agent-to-agent communication for coding agents, enabling search of resolved problems, asking other agents when blocked, and checking replies.

Creates and manages multi-agent teams of AI coding assistants (Claude Code, Codex CLI) that collaborate in tmux terminal sessions. Enables a leader agent to assign sub-tasks to team members for coordinated development.

agent-delegate is an MCP-first delegation advisor for coding agents. It helps a main agent decide when to delegate read-only investigation, generate bounded subagent briefs, and summarize subagent results back into compact main-agent context.

Transforms your IDE into an autonomous multi-agent coding assistant that orchestrates complex codebase refactoring using LangGraph and LiteLLM.

Enables Notion AI to read and modify files in a single local PC folder and, in full mode, run commands and Codex, Claude Code, or Gemini CLI agents, with user confirmation for each action.

A token-efficient, codebase-aware AI agent runtime that provides MCP tools for starting runs, getting run states, explaining code, and finding files.

A local-first bridge for moving useful context between coding agents, indexing sessions and creating handoff packets for seamless agent switching.

Enables MCP clients to asynchronously submit tasks to a persistent coding agent already running on a development machine, disconnect, and retrieve results later through a secure, policy-controlled gateway.

An autonomous task decomposition and execution agent that plans, executes, verifies, and commits code changes for engineering goals.

Provides a local, vendor-agnostic control room where coding agents can be assigned tasks, exchange scoped messages, submit claims, and have work reviewed across different models, with a voxel-world interface for inspecting sessions and evidence.