Build persistent memory and knowledge graphs for AI agents with hybrid search and context checkpoints. For developers integrating long-term state management and semantic retrieval into multi-turn agent workflows.
io.github.penfieldlabs/penfield-mcp
https://mcp.penfield.app/
HTTP
No auth required
How models use it and what it is built for.
Build persistent memory and knowledge graphs for AI agents with hybrid search and context checkpoints. For developers integrating long-term state management and semantic retrieval into multi-turn agent workflows.
Hosted endpoint — paste into any MCP client.
Where to find authoritative docs and source for Penfield Memory.
Paste any of these into Agent Studio after connecting Penfield Memory.
Common questions about connecting and running Penfield Memory.
What is Penfield MCP and what does it do?
Penfield MCP is a Model Context Protocol server that provides persistent memory and knowledge graph capabilities for AI agents. It enables hybrid search, context checkpoints, and semantic retrieval to maintain state across multi-turn conversations.
How do I connect to the Penfield MCP server?
The server is hosted at https://mcp.penfield.app/ and uses HTTP transport. You configure it as an MCP server endpoint in your client to enable persistent memory and knowledge graph features.
What is a context checkpoint and how do I use it?
A context checkpoint is a saved snapshot of conversation state that you can store and retrieve later. This allows agents to resume workflows, maintain long-term memory, and avoid re-processing the same context.
Does Penfield MCP support semantic search?
Yes, Penfield MCP provides hybrid search capabilities that combine keyword and semantic matching. This allows you to query your knowledge graph using both traditional search and vector-based similarity.
Can I use Penfield MCP to build knowledge graphs from my own data?
Yes, you can structure and store your data as knowledge graphs within Penfield MCP. The server supports building graphs from structured data and querying them via hybrid search and context retrieval.
Connect Penfield Memory to Claude, GPT, Gemini, DeepSeek and 60+ AI models in MCP Agent Studio. Compare answers side-by-side, save reusable agent presets, share runs — all in your browser, no install required.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams