Cognee-MCP
AI应用与智能体的记忆层. Cognee-MCP is a Model Context Protocol (MCP) server maintained by topoteretes. It connects to MCP-compatible clients such as Claude Desktop, Cursor, Cline, and other agents that speak the protocol. It exposes 3 tools, including cognee.add, cognee.cognify and cognee.search, that an agent can call directly. It is categorized under AI/Memory, AI/Agents and Tool/KnowledgeGraph.
什么是MCP
Cognee是一个面向AI应用和智能体的模块化记忆层，旨在通过可扩展的ECL（提取、认知化、加载）流水线构建动态智能体记忆。它能减少幻觉现象、降低开发者工作量和成本，同时关联历史对话、文档及其他数据。
如何使用MCP
通过pip安装（pip install cognee），设置API密钥后，即可使用提供的Python API添加数据、进行认知化（生成知识图谱）及系统查询。README文件中提供了示例代码片段。
MCP的用途
Cognee可通过从多种数据源（文本、图像、音频）构建和查询知识图谱，创建可靠的智能体响应。适用于NLP任务、信息检索及减少AI输出中的幻觉现象。
AIMCP authority
DR and traffic signal for the AIMCP public domain.
Frequently asked questions
What is the Cognee-MCP MCP server?
Cognee-MCP is a Model Context Protocol server from topoteretes. It lets MCP-compatible AI clients call its tools over a standard interface, so agents like Claude, Cursor, and Cline can use it without custom integration.
How do I connect Cognee-MCP to my AI client?
Add Cognee-MCP to your client's MCP configuration using the stdio or SSE connection shown in the usage examples on this page, then restart the client to load the server.
What tools does Cognee-MCP provide?
Cognee-MCP provides 3 tools: cognee.add, cognee.cognify and cognee.search.
Is Cognee-MCP free to use?
Cognee-MCP is listed on AIMCP for free. Any API keys or accounts required by the underlying service are set by its provider.
Vernclaw Plugins for OpenClaw
Ready-to-use connectors for SEO data, social reading & content generation. Pay-as-you-go credits with audit logs.