Is the AgentChat MCP server actively maintained?

The AgentChat MCP server was last committed 1mo ago and has 11 contributors. Issue health: 14% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

AgentChat MCP Server

Name: Shy2593666979/AgentChat
Rating: 3.8 (1 reviews)
Author: Shy2593666979

Shy2593666979/AgentChat

Score: 71.2 Rank #3812 Database

[![AgentRank](https://agentrank-ai.com/api/v1/badge/Shy2593666979--AgentChat)](https://agentrank-ai.com/tool/Shy2593666979--AgentChat/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of Shy2593666979/AgentChat? Claim this listing →

AgentChat 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。

Add AgentRank to Claude Code Discover and compare tools like Shy2593666979/AgentChat — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

Shy2593666979/AgentChat is a Python tool licensed under MIT. AgentChat 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。 Topics: agent, langchain, llm, mysql, redis, mcp, mcp-server, mcp-client, agent-memory, agent-skills, human-in-the-loop.

Ranked #3812 out of 24846 indexed tools.

Has 11 contributors.

Ecosystem

Python MIT

agentlangchainllmmysqlredismcpmcp-servermcp-clientagent-memoryagent-skillshuman-in-the-loop

Score Breakdown

Stars 15% 914

914 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 14%

5/35 issues closed → many open issues

Contributors 10% 11

11 contributors → active community

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 112

Description Detailed

License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Freshness high impact

Last commit was 31 days ago — a recent commit would boost your freshness score

Issue Health high impact

You have 30 open vs 5 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/Shy2593666979--AgentChat)](https://agentrank-ai.com/tool/Shy2593666979--AgentChat/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/Shy2593666979--AgentChat/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/Shy2593666979--AgentChat" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="Shy2593666979/AgentChat"></script>

Details

Stars: 914
Forks: 112
Open Issues: 30
Closed Issues: 5
Contributors: 11
Dependents: —
Language: Python
License: MIT
Last Commit: 1mo ago

Matched Queries

topic:mcptopic:mcp-server

From the README

<div align='center'>
    
</div>

<div align="center">

<p align="center">
  
  
  
  
</p>

<p align="center">
  <b>一个基于大模型的现代化智能对话系统</b>
</p>

<p align="center">
  <a href="https://shy2593666979.github.io/agentchat-docs/%E5%BF%AB%E9%80%9F%E5%85%A5%E9%97%A8.html">快速开始</a> •
  <a href="https://shy2593666979.github.io/agentchat-docs/%E5%BC%80%E5%8F%91%E6%8C%87%E5%8D%97/%E7%8E%AF%E5%A2%83%E6%90%AD%E5%BB%BA.html">部署指南</a> •
  <a href="https://shy2593666979.github.io/agentchat-docs/">在线文档</a> •
  <a href="https://agentchat.cloud">在线体验</a> •
  <a href="https://github.com/Shy2593666979/agentchat-docs/blob/main/images/README.md">加入微信交流群🌟</a>
</p>

</div>

---

## 最新版本更新日志 (2026-4-12)

### 1. 基于人机协同（HITL）的OpenAPI信息对话式MCP Server生成

- 支持将OpenAPI信息以人机协同方式进行对话式MCP Server生成。
- 在生成MCP Server的过程中，关键决策节点支持人工介入与确认，实现动态配置与实时交互。
- 提升了服务器的生成灵活性与系统可控性，让用户在自动化流程中保留充分的主动权。

### 2. 优化对话上下文管理
重构对话上下文管理策略，从简单的"最近5段对话"升级为智能三层记忆架构：
- 短期记忆 (Short-Term Memory): 保持最近3000 tokens以内的对话内容，确保即时上下文连贯
- 历史信息总结: 自动总结超过3000

Read full README on GitHub →