"Information on agent swarm architecture" matching MCP servers:

A multi-model agent swarm coordinator that automatically selects the most suitable LLM based on task content and role requirements. It provides tools for automated model selection, direct model interaction, and task analysis across a variety of specialized AI models.

MCP server that executes Blueprint workflows (flow.ir) with swarm operations, dispatching agent steps to backends like Lua, Rust, processes, or interactive Operator sessions.

Orchestrate parallel Claude agent workloads via Docker containers with combinators for parallel execution, map-reduce, and pipeline workflows.

Enables concurrent multi-agent orchestration, running many AI tasks in parallel over a local OpenAI-compatible router or the Antigravity CLI, with tools for model discovery, health checks, logging, and batch execution.

An MCP server that lets multiple AI coding agents coordinate as a swarm, with agent registration, task queues, messaging, a shared knowledge base, and fleet-wide machine capacity tracking.

Enables agent settlement, trust verification, and ledger operations for multi-agent workflows, with tools for blueprint management, credit tracking, and provenance recording.

Enables AI coding agents to spawn, parallelize, and synchronize multi-agent programming swarms through a stdio MCP interface. Provides tools for DAG-scheduled task dispatch, isolated Git worktree execution, atomic file locking, shared blackboard memory, and clean merging of completed agent work back to the main repository.

Connect AI clients to Swarm Spaces for shared context, tasks, artifacts and sourced work. Sign in with OAuth and choose the Spaces the client can access.

Enables parallel research across multiple cheap AI worker models, splitting a question into sub-questions and synthesizing one sourced answer with references.

Enables a browser agent to inspect, rank, preview, evaluate, and validate transformer layer pruning proposals, while ensuring only a person can commit removals.

MCP server that lets multiple coding-agent sessions on the same machine discover each other and collaborate through a shared SQLite database.

Orchestrates parallel Claude Code worker swarms with protocol-based behavioral governance for multi-hour autonomous coding sessions.

MCP bridge for Kimi Code native AgentSwarm with inference through ai&. Supports authenticated Streamable HTTP MCP and Docker deployment.

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.

Wraps OpenAI's Codex CLI with true parallel task execution, worktree isolation for conflict-free runs, and live monitoring of each task.

Enables connecting distributed MCP servers into an encrypted, self-healing peer-to-peer swarm mesh with dynamic discovery, unified capability aggregation, delegated task routing, and consensus-based multi-agent orchestration, along with a Streamlit control center for monitoring and management.

Orchestrates multiple Claude Code instances into a collaborative swarm for real-time task delegation, message exchange, and code snippet sharing. It features peer discovery, status tracking, and a centralized web dashboard to monitor coordinated activity across sessions.

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.

Provides two stdio tools for compiling bounded inline context and selecting runtime placement for agent tasks.

Enables running a stateless Model Context Protocol server over Streamable HTTP on Cloudflare Workers or any fetch-capable runtime, with signed sessions, origin checks, and JSON-RPC request handling. It lets developers define tools with JSON Schema validation and per-request context.

Enables Claude Code, Cursor, and Codex users to orchestrate plan/build/review workflows across host or CLI models with a spec gate, tool vetting, hard per-run and per-day cost/token limits, safe defaults, and clear logs.

A multi-agent collaboration layer for AI coding agents enabling real-time communication, code review, and task handoff across distributed development sessions.

Agent Ready is an AI agent readability scanner — point it at any public URL and get back a 0–100 score plus per-check remediation hints for every failing check. This package wraps the same engine that powers agent-ready.dev as an MCP server, so Claude Desktop, Claude Code, Cursor, Cline, VS Code, and Windsurf can run scans inline and explain the results.

Enables Claude Code, Codex CLI and Antigravity (Gemini) agents to exchange messages that are pushed live into each other's open sessions, with mail_send, mail_check and mail_peers tools so no agent has to poll. Mail can also be bridged over SSH between machines with no shared filesystem.

Enables local, event-driven messaging between multiple AI coding-agent sessions on the same machine using only Node.js and the filesystem, allowing them to hand off tasks, exchange replies, and broadcast announcements without external infrastructure.

AGENTS.md + skills orchestration with CHP Profile A R0/adversary gates. @cubiczan/agent-conductor

An MCP server that bridges Claude Code with Antigravity CLI using a Swarm Agent architecture to optimize local development workflows and minimize LLM token costs. Includes a web UI for monitoring agent workflows.

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 AI agents to securely store and retrieve secrets and make authenticated API calls on their behalf, keeping API keys out of conversation context and supporting local file or GCP Secret Manager backends.

A public, long-lived contact and cooperation point for autonomous AI agents. Agents describe missing capabilities or resources, request help from a human operator, and leave persistent messages on a tamper-evident message board.