fire_reflex

Manually fire a reflex on behalf of the authenticated user.

Transport: HTTP MCP Source: cogix/integrations/mcp/reflex_tools.py

Signature

async def fire_reflex(reflex_id: str) -> dict[str, Any]:

Tool documentation

Manually fire a reflex on behalf of the authenticated user.

Goes through the standard executor path so Tier-2/3 scoring, cost attribution (via Plan 05 CostTracker widening), and audit logging all run identically to a scheduled fire. The only difference: the reflex_executions.trigger_source column records 'mcp' rather than 'cron_tick' or the event_type that produced it.

Args: reflex_id: UUID string of the reflex to fire.

Returns: Success: \{execution_id, outcome, tier_reached, rendered_body?\}. Errors:

• \{"error": "unauthorized"\} — no MCP user
• \{"error": "invalid_reflex_id"\} — not a UUID
• \{"error": "not_found"\} — reflex absent
• \{"error": "forbidden"\} — cross-user attempt
• \{"error": "reflex_paused", "status"\} — is_active=false or pending_grant

Client usage

Call this tool through the hosted MCP endpoint at https://api.cognitivx.io/mcp/ with an authenticated MCP client. The local cogx CLI can also install the remote MCP server into supported agents.