"Categorizing messages such as emails or system logs" matching MCP servers:

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 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.

Exposes the local Claude Code CLI as a subagent for Codex, enabling background review and implementation jobs with two fixed permission tiers.

Delegates work from MCP clients (like Claude Code) to the Codex CLI, allowing spawning of autonomous Codex subagents for tasks.

Exposes a running DeepSeek Harness as an MCP endpoint so any other agent or script can create workspaces and sessions, hand coding tasks to the DSH agent, read and write files, run shell commands, and invoke permitted harness tools under the same sandbox, transcript, and permission policy as the DSH UI.

Enables dispatching entire autonomous multi-agent engineering swarms directly from IDEs like Cursor and Windsurf via a single MCP endpoint, with streaming progress updates and verified git diffs returned to the editor.

Enables Claude Code, Cursor, and other AI tools to call OpenAI Codex for task execution, with safe and writable modes.

Delegates coding tasks to the local Claude Code CLI via MCP, offering run, review, and status tools for MCP-compatible agents.

Enables AI coding agents to read and write a user's Figma file through the Figma Plugin API, offline and privately, without API tokens or rate limits.

Enables users to generate complete, production-ready software projects from simple ideas by coordinating 8 specialized AI agents through the Model Context Protocol.

A minimal local MCP server that lets Claude Desktop or Claude Code delegate coding tasks to Grok Build running headless as a subagent.

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.

Wraps the Claude Agent SDK as MCP servers, letting you spawn multiple specialized Claude Code agents — each with its own model, tools, system prompt, and personality — from any MCP client.

This MCP server enables LLM hosts to plan large tasks and delegate subtasks to specialized local CLI agents, such as Codex and Claude Code, using tools like delegate_task and get_agent_roster.

An MCP server that lets Claude Code delegate coding tasks such as code generation, review, refactoring, and test writing to a local Ollama instance running a Qwen3 model.

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.

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

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.