MCP (Model Context Protocol)

RememberOS speaks MCP over HTTP — point Claude Desktop, Claude Code, or any MCP client at it and your agent gets memory tools.

Endpoint#

POST https://rememberos.ai/v1/mcp        (JSON-RPC 2.0)
Authorization: Bearer mv_…

Calling tools#

The endpoint speaks four JSON-RPC methods: initialize, ping, tools/list, and tools/call. The tools below are not methods — you invoke each one through tools/call, passing its name in params.name and its arguments in params.arguments. (An MCP client like Claude Desktop or Claude Code does this for you; the raw calls below are for testing by hand.)

# discover the tools
curl -s https://rememberos.ai/v1/mcp \
  -H "Authorization: Bearer $REMEMBEROS_API_KEY" -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

# call a tool — note: NOT {"method":"list_collections"}
curl -s https://rememberos.ai/v1/mcp \
  -H "Authorization: Bearer $REMEMBEROS_API_KEY" -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call",
       "params":{"name":"list_collections","arguments":{}}}'

A result comes back as {"result":{"content":[{"type":"text","text":"…"}]}} — the tool's JSON payload is the string in that text field.

Tools#

Tool	Args	Does
`search_memory`	query, collection?, limit?	hybrid search
`store_memory`	text, collection?, category?	store a memory
`get_memory`	id	fetch one memory
`list_collections`	—	your collections + counts
`related_memory`	id, limit?	nearest neighbours of a memory — discover connected observations
`what_changed`	collection, limit?	where a newer fact superseded an older one (`{current, superseded}` pairs)
`collection_health`	collection, stale_days?	total / stale / expired / supersessions + a `needs_attention` roll-up
`summarize_collection`	collection, limit?	board-report briefing — `{summary, themes, based_on}`
`find_duplicates`	collection, threshold?	near-duplicate clusters (read-only preview; deletes nothing)
`archive_stale`	collection, older_than_days?, dry_run?	soft-archive stale memories (reversible; `dry_run` defaults true)

The first four tools carry knowledge in and out; related_memory, what_changed, and collection_health are discovery primitives — they let one agent surface patterns, trends, and drift in knowledge a different agent recorded; while find_duplicates and archive_stale let agents maintain the shared memory. That is the point of a shared memory layer: the agent that writes an observation is rarely the one that acts on it.

Agent patterns#

Recall-first: call search_memory with the user's intent before answering; cite what you find.
Learn-after: when the user states a durable fact or preference, call store_memory.
Use one collection per project, or container tags per end-user (set via the REST API/SDKs — MCP tools keep the minimal surface).

For the one-paste setup prompt, see Install with AI. To wire agents from several vendors into one shared collection, see Connect every agent.

PreviousFramework Adapters NextEmail Drop