Agent Dispatch
@ginkida
About Agent Dispatch
Let Claude Code agents delegate tasks to agents in other project directories, with parallel dispatch, sessions and async jobs.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"agent-dispatch": {
"command": "agent-dispatch",
"args": [
"serve"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Agent Dispatch?
Agent Dispatch is an MCP server and CLI that lets Claude Code agents delegate tasks to agents running in other project directories. Each target agent has its own CLAUDE.md, MCP servers, and tools, creating a team of specialists instead of a single generalist. It is written in Python and hosted on GitHub.
How to use Agent Dispatch?
Agent Dispatch is run as both an MCP server and a CLI tool. Installation and configuration instructions are available in the GitHub repository at https://github.com/ginkida/agent-dispatch.
Key features of Agent Dispatch
- Parallel dispatch across multiple agents
- Multi-turn sessions and async jobs
- Agent-to-agent dialogue
- Self-hosted, no cloud vendor required
- Each agent uses its own CLAUDE.md and MCP tools
Use cases of Agent Dispatch
- Running multiple specialized agents concurrently for complex, multi-step projects
- Delegating long-running tasks asynchronously without blocking the primary agent
- Facilitating agent-to-agent conversations for collaborative problem solving
- Using different MCP configurations and tools tailored to each sub-task
FAQ from Agent Dispatch
What capabilities does Agent Dispatch offer?
It supports parallel dispatch, multi-turn sessions, asynchronous jobs, and direct agent-to-agent dialogue.
Is Agent Dispatch hosted in the cloud?
No, it is self-hosted with no dependency on a cloud vendor.
How does Agent Dispatch differ from using a single agent?
It organizes agents as specialists—each with its own CLAUDE.md and MCP servers—so you get targeted expertise rather than one generalist handling everything.
Where can I find the code and documentation?
The code and documentation are available on GitHub at https://github.com/ginkida/agent-dispatch.
Frequently asked questions
What capabilities does Agent Dispatch offer?
It supports parallel dispatch, multi-turn sessions, asynchronous jobs, and direct agent-to-agent dialogue.
Is Agent Dispatch hosted in the cloud?
No, it is self-hosted with no dependency on a cloud vendor.
How does Agent Dispatch differ from using a single agent?
It organizes agents as specialists—each with its own CLAUDE.md and MCP servers—so you get targeted expertise rather than one generalist handling everything.
Where can I find the code and documentation?
The code and documentation are available on GitHub at https://github.com/ginkida/agent-dispatch.
Basic information
More AI & Agents MCP servers
Web Agent Protocol
OTA-Tech-AI🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
bsv.cx
Andy RoweTimestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei
Model Context Protocol Server for Home Assistant
tevonsbA MCP server for Home Assistant
欢迎来到 智言平台
Shy2593666979AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。
Comments