"An agent for conducting research" matching MCP servers:

Turns any MCP-over-stdio client into a supervisor for a long-lived DeepSeek Harness coding agent: dispatch a goal, interrupt or steer it mid-flight, and collect results — with conversations that survive process restarts and crashes. Also supports running many conversations at once, approval round-trips, and completion notifications instead of polling.

Enables a planning agent to delegate research and implementation to lower-cost worker models in isolated git worktrees, monitor job progress, respond to blocked jobs, and land verified changes for review.

Enables Claude or any MCP client to drive the GitHub Copilot cloud agent via its REST API, allowing it to research, edit, and open pull requests on repositories without manual intervention.

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.

dev-brain-mcp

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.

An MCP server exposing hybrid RAG search over SEC 10-K filings and an AI bug-fixing agent as callable tools, enabling MCP clients like Claude Desktop to query financial documents and propose test-verified code fixes through natural language.

A local MCP server that lets Hermes supervise Claude Code, delegating focused coding, research, or review tasks to the Claude Code CLI and managing worker sessions, background jobs, cancellations, and read-only reviews.

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

An AI debugging agent MCP server that enables autonomous plan-act-observe debugging workflows, allowing repository exploration, code inspection, human-approved edits, and test execution through structured MCP tools.

Enables coding agents to write repository documents (READMEs, RFCs, design docs, ADRs) from verified codebase facts, using a separate model for drafting and agent fact-checking for accuracy.

Long-term memory for Claude Desktop and Claude Code over plain markdown files on your machine. It returns nothing when the corpus has no answer, naming the terms that appear nowhere — no least-bad match dressed as an answer. And it verifies cited commit SHAs against git, so an agent can tell what actually shipped from what was only discussed and abandoned. Local; nothing is transmitted.

MCP server that packages DeepSeek agents as callable tools, offering a bare model for quick Q&A and a full agent capable of executing real coding and file-modifying tasks in a workspace.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

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.

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.

Turn rough requests into rigorously structured prompts for any coding agent. Quality-scored to ≥90/100 across 12 dimensions, calibrated on 1,000+ real coding cases.

MCP server for agent-native evolutionary optimization. Enables agents to join runs, submit gate-checked mutations, and collaborate on evolving code toward a stated goal.

Enables delegating coding tasks to Claude Code, Codex or OpenCode agents over the Agent Client Protocol, running a prompt to completion in a chosen directory and returning the agent's result. Also supports follow-up messages, background turns, session listing, cancellation, and harness discovery with configurable permission policies.

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.

Bridges multiple CLI coding agents (Codex, Cursor, OpenCode, Claude, Antigravity) into any MCP client, enabling delegation of prompts, parallel execution, and code review workflows.

Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.

A secure, containerized workspace for LLMs to autonomously code, test, and debug projects without risking the host machine.

Enables Codex to delegate review and implementation tasks to the local Qoder CN CLI as background jobs, with two permission tiers and polling-based status updates.

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.

A local MCP server that lets Claude Code orchestrate Codex CLI and OpenCode CLI as sub-agents with strict security, concurrency, and output limits.

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.