MCP Knowledge Ops

Positioning: mcp_knowledge_ops is an internal component of the MakeMind knowledge stack exposed through the mcp_knowledge facade. Application code should import package:mcp_knowledge/mcp_knowledge.dart — the symbols declared here are re-exported from there. Direct package:mcp_knowledge_ops/ imports remain valid for advanced or integration scenarios but are discouraged in product code.

A stateless orchestration layer for MakeMind. Coordinates pipelines, workflows, scheduling, runbooks, and observability across the ecosystem; persistence is delegated to mcp_fact_graph.

Components

• Execution Engine — central coordinator for pipeline / workflow runs.
• Pipelines — staged data processing with gates and metrics. Built-in pipelines: curation, summary refresh, pattern mining, ingest, index rebuild, cascade refresh, clustering.
• Workflows — long-running build/release flows with reviews, approval routing, and cancellation.
• Scheduler — cron / event / deadline triggers, MCP tools integration, scheduler events.
• Runbooks — operational procedures.
• Observability — logging, metrics, tracing, structured events.
• Standard port adapters — implements mcp_bundle ops Contract Layer (workflow / pipeline / runbook / runs / schedule trigger / audit).

Quick Start

import 'package:mcp_knowledge_ops/mcp_knowledge_ops.dart';

final handlers = HandlerRegistry();
handlers.register('myHandler', MyHandler());

final engine = ExecutionEngine(
  config: ExecutionEngineConfig(),
  handlers: handlers,
);

final result = await engine.executePipeline(pipeline, input, context);

Support

• Issue Tracker
• Discussions

License

MIT — see LICENSE.