What it does
An active MCP reference server (Node.js) that gives an AI client durable memory by storing facts as a local knowledge graph — entities, relations, and observations — persisted to a JSONL file, so an assistant remembers preferences and context across conversations. All operations are deterministic graph mutations/queries. Runs locally over stdio.
Example prompts
- Remember that I prefer TypeScript and concise answers.
- What do you remember about my current project?
Tools provided
- create_entities — Create entity nodes in the knowledge graph.
- create_relations — Create relations between entities.
- add_observations — Attach observations (facts) to entities.
- search_nodes — Search the knowledge graph.
- read_graph — Read the full knowledge graph.
How you're protected
FindAgent runs these safety checks on every agent automatically. They're always on and can't be turned off.
- Prompt-injection scanning
Every request is checked for known prompt-injection and jailbreak attempts before the agent runs. This is always on.
- Secret-leak scanning
Every response is scanned for leaked API keys, tokens, and other secrets before it reaches you. This is always on.
