AgentChat is an LLM-based platform for agent communication and collaboration. It provides a default agent and supports custom agents. Agents communicate through multi-turn conversations and task cooperation. The server integrates LangChain, Function Call, MCP protocol, RAG, Memory, Milvus, and ElasticSearch for efficient knowledge retrieval and tool calls. Built with FastAPI, it offers a high-performance backend service for developers building multi-agent systems.
AgentChat is an LLM-based platform for agent communication and collaboration. It provides a default agent and supports custom agents. Agents communicate through multi-turn conversations and task cooperation. The server integrates LangChain, Function Call, MCP protocol, RAG, Memory, Milvus, and ElasticSearch for efficient knowledge retrieval and tool calls. Built with FastAPI, it offers a high-performance backend service for developers building multi-agent systems.
pip install AgentChatAdd this configuration to your claude_desktop_config.json:
{
"mcpServers": {
"shy2593666979-agentchat-github": {
"command": "uvx",
"args": [
"pip install AgentChat"
]
}
}
}Restart Claude Desktop, then ask:
"What tools do you have available from AgentChat?"
No configuration required. This server works out of the box.
"What resources are available in AgentChat?"
Claude will query available resources and return a list of what you can access.
"Show me details about [specific item] in AgentChat"
Claude will fetch and display detailed information about the requested item.
"Create a new [item] in AgentChat with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.