
A2CR
@a2cr
关于 A2CR
MCP server for AI-agent handoffs. A2CR saves client-encrypted WorkBaton checkpoints and WorkStash notes so MCP-capable clients can resume work without passing full chat history.
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"a2cr": {
"command": "a2cr-mcp",
"args": [],
"env": {
"A2CR_BASE_URL": "https://a2cr.app"
}
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is A2CR?
A2CR is an MCP server for AI-agent handoffs. It saves client-encrypted WorkBaton checkpoints and WorkStash notes so MCP-capable clients can resume work without passing full chat history.
How to use A2CR?
Install the package with python -m pip install --upgrade a2cr-mcp. After installation, configure your MCP client to run the server – no additional configuration commands are documented.
Key features of A2CR
- Facilitates AI-agent handoffs between sessions
- Saves client-encrypted WorkBaton checkpoints
- Stores WorkStash notes for context transfer
- Enables resuming work without full chat history
- Lightweight Python package available on PyPI
Use cases of A2CR
- Continue long-running AI conversations across multiple sessions
- Transfer agent state and notes between different MCP clients
- Persist encrypted checkpoints for secure context retention
FAQ from A2CR
—
AI 与智能体 分类下的更多 MCP 服务器
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。
Perplexity Ask MCP Server
ppl-aiThe official MCP server implementation for the Perplexity API Platform
MCP-LLM Bridge
patruffBridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools
meGPT - upload an author's content into an LLM
adriancoCode to process many kinds of content by an author into an MCP server
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
评论