Docs
Refer a friend. Get a weekly-quota reset.Friend signs up and uses it → +1 reset (valid 30 days) · up to 10% cash back on their spend.
+1 resetGenerate link

MCP host integration

Configure a stdio host and understand the four model tools and fixed identity scope.

Configure the host

Point the MCP command to the built rsia executable. Adapt the outer configuration to the host:

json
{
  "mcpServers": {
    "rsiagent": {
      "command": "/absolute/path/to/rsia",
      "args": ["mcp", "--data", "/absolute/path/to/rsia.sqlite3", "--namespace", "personal", "--actor", "my-assistant"]
    }
  }
}
{
  "mcpServers": {
    "rsiagent": {
      "command": "/absolute/path/to/rsia",
      "args": ["mcp", "--data", "/absolute/path/to/rsia.sqlite3", "--namespace", "personal", "--actor", "my-assistant"]
    }
  }
}

Reconnect and confirm the four tools. A successful connection does not automatically wire the host's task context and execution receipts into the complete improvement cycle.

Model tools

ToolPurposeBoundary
evo_prepareReturn a fixed snapshot of approved active skillsDoes not execute the host task
evo_feedbackRecord reported run feedbackSelf-report is not independent scoring
evo_proposeSubmit a bounded proposal for validationDoes not approve or publish it
evo_inspectRead an authorized redacted objectDoes not grant admin or raw-data access

Use the schemas advertised by the current server. Do not invent identity fields to elevate a request.

Identity and verification

The stdio entry fixes the Agent identity at startup. Namespace scopes data and actor identifies the caller. Management requires a separate entry and credential; see management.

Verify initialization and tools/list, prepare a snapshot, confirm that the host actually attaches it, execute the task and send feedback. See the lifecycle for stronger evidence than successful tool calls.