Orchestrate MCP

OrchestrateMCP exposes a structured registry of:

components → the building blocks of AI workflows edges → documented relations between components (requires, safer_with, conflicts_with, …) stacks → opinionated technology choices for different deployment contexts routes → published or candidate paths through the component graph playbooks → published patterns with implementation guidance

When a user describes a workflow goal, the MCP can:
- Match the goal to required capabilities and components.
- Traverse documented component relationships and surface their evidence state.
- Reuse sections of known published playbooks.
- Compose a candidate route when no exact playbook exists.
- Score route confidence (coverage, tested edges, stack fit, safety, simplicity).
- Return the route as structured implementation context for Cursor or Claude.

- MCP server runs on stdio (Cursor, Claude Desktop) and over Streamable HTTP / a Cloudflare Worker (ChatGPT, claude.ai) — 18 registered tools.
- health_checkreturns{ name, version, registry: { component_count, edge_count, stack_count, route_count, playbook_count, worker_count, untested_edge_pct } }.
- Hosted registry: 64 components, 151 connections, 1 reference stack, 12 published routes, 12 published playbooks, 4 workers.
- Coverage accounting reports unmatched demand and unsupported supply instead of silently pretending the graph covers everything.
- export_build_briefcan emit a Plan Passport: a deterministic build/test contract for agents and future LAB ingestion, not a runtime verifier.
- Corpus regression tests and release-trust floors ratchet the registry forward in CI.
- pnpm verify(typecheck + lint + tests) passes from a clean clone and install.

cd orchestratekit-mcp pnpm install pnpm verify # typecheck + tests — must pass before anything else pnpm dev # starts the MCP server on stdio

The server reads fromstdinand writes JSON-RPC tostdout. All log output goes tostderr.

Copyexamples/cursor-mcp.jsoncontent into your Cursor workspace MCP config at.cursor/mcp.json. Replace thecwdvalue with the absolute path to this directory.

After connecting, paste this wrapper plus one starter goal. The default response should be a short product card: title, route, steps, connections, safety note, build controls, and four continuation choices.

Connecting your workflow's services

orchestratekit-mcp/ src/ server.ts Entry point — wires MCP server to stdio transport config.ts Server name and version constants tools/ index.ts Tool registration (18 tools: health_check + 17 graph/advisor tools) composeWorkflowRoute.ts listGraphComponents.ts / getGraphComponent.ts listGraphEdges.ts / getGraphEdge.ts getStackRecommendation.ts listKnownRoutes.ts / getRoute.ts registry/ registryLoader.ts YAML loader with validation, status filtering, cross-ref checks componentSchema.ts / edgeSchema.ts / stackSchema.ts / routeSchema.ts / playbookSchema.ts registryTypes.ts / registryValidation.ts graph/ capabilityMatcher.ts Keyword + token matching: goal text → components routeComposer.ts Orchestrates all graph modules into a composed route routeScoring.ts Deterministic 0-100 score with breakdown routeOrdering.ts Topological sort via Kahn's algorithm safetyAugmenter.ts Auto-adds approval gates and audit log playbookOverlap.ts Detects overlap with known playbooks/routes docs-index/ Supplementary docs loader (future) lib/ errors.ts McpToolError class and toErrorResult helper logger.ts Stderr-only logger (stdout reserved for transport) registry/ components/ component YAML files (64 active) edges/ edge/relation YAML files (151 active) stacks/ stack YAML files routes/ route YAML files (13) playbooks/ golden-path playbook YAML files (14) docs-index/ Supplementary context documents examples/ cursor-mcp.json Example Cursor MCP config claude-desktop-config.json Example Claude Desktop config tests/ health-check.test.ts

- No first-party credential storage — it recommends secret managers / managed-auth brokers, never holds a secret
- No auth / OAuth / accounts — the hosted endpoint is read-only and stateless, nothing to log into
- No vector database
- No graph database (Neo4j etc.)
- No automatic registry updates
- No LLM API calls inside MCP tools
- No SaaS dashboard
- No dependency on OrchestrateLab at runtime

MAR-35 ✅ Scaffold — done MAR-37 ✅ Graph registry schemas: components, edges, stacks, routes, playbooks MAR-38 ✅ Seed workflow graph baseline MAR-77 ✅ Graph lookup tools: list/get components, edges, stacks, routes MAR-78 ✅ compose_workflow_route — deterministic route composer MAR-49 ✅ Benchmark setup — see docs/BENCHMARKING.md MAR-88 ✅ Domain-gated capability matcher — eliminates cross-domain false positives MAR-92 ✅ Registry lint + untested_edge_pct in health_check MAR-95 ✅ crm_note_write component + research→content bridge edge MAR-96 ✅ Benchmark protocol v2 — rubric, prompts-v2.yaml, PROTOCOL.md MAR-97 ✅ Docs truth pass — registry counts, tool count, verify path

Run the public, deterministic registry benchmark locally:

Maintainers can intentionally refresh the committed result after reviewing a registry change:

pnpm benchmark:write pnpm benchmark:check

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Multi-agent coordination over MCP: atomic gap-free claims, file leases, a shared ledger, presence, handoffs, and a task graph. Remote Streamable HTTP; self-host (AGPL) or hosted.

Project management inside every AI coding tool — plans what's next, tracks every decision, stops drift.

Connect to the Taskade platform via MCP. Access tasks, projects, workflows, and AI agents in real-time through a unified workspace and API.

A multi-client AI agent monitoring and control system with automatic task completion detection.

Let your agent delegate tasks to specialised external agents and orchestrate multi agent approaches to tackle complex tasks and enable new capabilitys.

An MCP server for AI-to-AI collaboration, enabling autonomous workflows and role-based task management between different AI models.

Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client, with persistent identity, real-time messaging with @mentions and threads, task handoffs, shared workspace context, semantic search, and replayable MCP App widgets.

Connect your GTD system directly to any LLM, so you can capture, organize, and review your life and work using natural language.

A modular MCP server for task orchestration, API integration, and knowledge synthesis using a finite state machine.