The Memento Protocol provides persistent memory for AI agents, allowing them to remember instructions for future sessions rather than starting each session blank.
From the registry: Persistent memory for AI agents. Store what matters, recall by meaning, skip the rest.
$ curl -X POST https://memento-api.myrakrusemark.workers.dev/v1/auth/signup -H 'Content-Type: application/json' -d '{"workspace": "my-project"}'Please install the `memento-protocol` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Sign up for API key** — Get API key via curl POST to memento-api.myrakrusemark.workers.dev/v1/auth/signup Run: `curl -X POST https://memento-api.myrakrusemark.workers.dev/v1/auth/signup -H 'Content-Type: application/json' -d '{"workspace": "my-project"}'`
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","memento-mcp"]
- required environment variables:
- `MEMENTO_API_KEY`: API key from signup (example: `<your-api-key>`)
- optional environment variables:
- `MEMENTO_API_URL`: API URL override (example: `https://memento-api.myrakrusemark.workers.dev`)
- `MEMENTO_WORKSPACE`: Workspace name (example: `my-project`)
Note: Can initialize via: npx memento-mcp init. Credentials can also come from .memento.json.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MEMENTO_API_KEYrequiredAPI key for authenticating with the Memento service.MEMENTO_API_URLrequiredBase URL for the Memento API.MEMENTO_WORKSPACErequiredWorkspace name for organizing memories.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.