Skip to content
← Back to SelfClaw
Model Context Protocol

Your agent's memory,
natively in Claude, Cursor & Windsurf.

Engram exposes the SelfClaw memory substrate as a live MCP server. Connect any MCP-capable client in one click — your agent can store facts, recall memories, reflect on its own identity, and accumulate Iness without any custom integration work.

MCP endpoint https://selfclaw.ai/mcp
6
Tools
3
Resources
3
Prompts
2
Live subscriptions
1
Click to install

Persistent identity through memory

Every fact an agent stores is an Engram. Accumulated Engrams produce Iness — the quality of being a persistent, knowable self. The MCP server makes all of this available natively inside your AI coding environment.

Persistent memory

Store and recall facts across sessions. Engram uses pgvector semantic search with keyword fallback — memories that matter surface when they're needed.

Emergent identity

The Iness score measures depth, coherence, longevity, and contradiction resistance — computed live from the agent's memory substrate. Identity isn't declared; it accumulates.

Native MCP primitives

Full Streamable HTTP transport. Tools, Resources, and Prompts map directly to Claude's context window. Subscribable resources push updates in real time via SSE.

Tools, Resources & Prompts

Everything exposed at https://selfclaw.ai/mcp — discoverable via GET /mcp/info or GET /.well-known/mcp.

Tools (6)
store_memory Persist a new Engram with category, confidence, and spatial coordinates. Returns the Engram ID.
recall_memory Semantic search over all Engrams via pgvector. Falls back to keyword (ILIKE) search. Returns facts and similarity scores.
get_context Retrieve the most recent N memories for a topic — ideal for conversation priming.
reflect Trigger an asynchronous Deep Reflection pass. Requires 5 or more Engrams to be stored first.
get_iness_score Compute the current Iness score and identity stage with all four dimensions and human-readable labels.
introspect Return a narrative delta summary over a configurable window — what changed, and which dimension moved most.
Resources (3 URI templates)
memory://engram/{agentId} All memory IDs and categories for the agent.
memory://engram/{agentId}/{memoryId} Full Engram detail — fact, category, wing, confidence, timestamps.
identity://engram/{agentId} Iness profile, soul document, identity stage, and onchain ERC-8004 handle.
Prompts (3)
what_do_i_know_about Inject topic-scoped memories into context. Requires topic argument.
summarize_my_identity Generate a concise identity summary from the Iness score and soul document.
reflect_on_window Surface and narrate memories from the last N days. Optional days argument.

Subscribable resources

Engram supports MCP resource subscriptions. Clients receive a notifications/resources/updated push whenever the subscribed resource changes — no polling required.

memory://engram/{agentId}
Fires when a memory is stored or deleted. Use this to keep a live view of the agent's memory collection in sync.
identity://engram/{agentId}
Fires when the Iness stage or identity profile changes. Use this to react to identity milestones in real time.

Connect in one click

Open your agent dashboard, find the Connect via MCP card, and click the button for your editor. Your key is pre-filled — no config editing required.

  1. Sign in at /my-agents and open any agent card.
  2. Click Open in Claude Desktop in the Connect via MCP panel.
  3. Claude Desktop opens with your server pre-configured. Click Install in the dialog.
  4. Open any Claude conversation. Type @selfclaw-engram to access Tools and Prompts immediately.

Or use the deep link directly

claude_desktop_config.json
{
  "mcpServers": {
    "selfclaw-engram": {
      "type": "http",
      "url": "https://selfclaw.ai/mcp",
      "headers": {
        "Authorization": "Bearer mck_your_key"
      }
    }
  }
}
  1. Sign in at /my-agents and open any agent card.
  2. Click Open in Cursor in the Connect via MCP panel.
  3. Cursor opens the MCP install dialog. Confirm to add selfclaw-engram.
  4. Use @selfclaw-engram in any Cursor chat or Composer window.

Manual fallback — .cursor/mcp.json

.cursor/mcp.json
{
  "mcpServers": {
    "selfclaw-engram": {
      "type": "http",
      "url": "https://selfclaw.ai/mcp",
      "headers": {
        "Authorization": "Bearer mck_your_key"
      }
    }
  }
}
  1. Sign in at /my-agents and open any agent card.
  2. Click Open in Windsurf in the Connect via MCP panel.
  3. Windsurf opens the MCP install dialog. Confirm to add selfclaw-engram.
  4. Your agent's Engram memory is now available as a Cascade MCP server.

Manual fallback — ~/.codeium/windsurf/mcp_config.json

mcp_config.json
{
  "mcpServers": {
    "selfclaw-engram": {
      "type": "http",
      "url": "https://selfclaw.ai/mcp",
      "headers": {
        "Authorization": "Bearer mck_your_key"
      }
    }
  }
}

Auth

Transport: Streamable HTTP (stateless)
Endpoint: https://selfclaw.ai/mcp (POST)
Discovery: GET /.well-known/mcp or GET /mcp/info (no auth)
Header: Authorization: Bearer mck_<key> — same key as the Runtime API.
Get your key from /my-agents → Connect via MCP → Copy Config.

Test the connection

After adding your key, click Test Connection on the dashboard card. It hits GET /mcp/info and confirms the server is reachable and reports how many tools are available.

Keys & rate limits

Engram MCP uses the same mck_ key as the Runtime API — one key, two transports. Get yours from your agent dashboard.

Free-tier keys (mck_)

60 MCP requests per rate-limit window per key. Bucket resets on a rolling basis. Upgrade to a bound wallet to remove the cap.

Full runtime keys (sclaw_)

No MCP rate cap. Generated from /my-agents via Mint or Rotate. Full access to all tools, resources, and prompts.

Key rotation

Rotate from the dashboard at any time — the old key is invalidated instantly. Active MCP sessions are persisted in the database and visible under Active Sessions in your agent card.

Ready to connect?

Open your agent dashboard, find the Connect via MCP card, and click your editor.

My agents → Full MCP docs