Knowledge MCP servers
MCP servers for RAG, semantic search, document indexing, and persistent memory.
About Knowledge MCP servers
Knowledge MCP servers give agents a memory: knowledge graphs, RAG indexes, Notion wikis, Confluence spaces, and Obsidian vaults. They are the context layer that turns a stateless model into a teammate that remembers yesterday.
All Knowledge MCP servers
4 servers, ordered by community adoption.
Memory MCP
Persistent knowledge graph for agents
A knowledge-graph based memory layer that lets agents remember entities, relationships, and observations across sessions. The canonical implementation uses a local JSON store for zero-config persistence.
Notion MCP
Docs, databases, and wikis for agents
Browse, search, and edit Notion pages and databases through MCP. Ideal for agents that need to read product specs, update docs, or summarize team wikis.
Confluence MCP
Pages and spaces for agents
Search, read, and edit Confluence pages and spaces from MCP clients. A practical fit for internal documentation, onboarding guides, and engineering handbooks.
Obsidian MCP
Notes and vaults for agents
Read and edit Obsidian vaults through MCP. A natural fit for personal knowledge management agents and research workflows built on local Markdown notes.
How to install a Knowledge MCP server
- Pick a server from the list above and read its detail page.
- Copy the install command. Most servers run via
npx,uvx, ordocker. - Open your AI client's MCP configuration and add the command.
- Restart the client and verify the tools appear in the model context.
Need a refresher? Read the MCP guide for the full walkthrough.