Skip to content

CLI and MCP Surface

Nick edited this page Jun 21, 2026 · 3 revisions

CLI And MCP Surface

CW is CLI-backed and MCP-first.

The CLI is the lowest common denominator: every serious coding agent can run shell commands. MCP is the cross-app integration surface for hosts that support tools and resources.

This page vs CLI MCP Parity. This page is the catalog — how to USE the two surfaces (which commands and cw_* tools exist, and the flow they drive). CLI MCP Parity is the guarantee — the mechanism (the capability registry) and the fail-closed gate that keeps the two surfaces from ever drifting apart.

CLI Quick Start

cd plugins/cool-workflow
node scripts/cw.js list
node scripts/cw.js app list
node scripts/cw.js app show architecture-review
node scripts/cw.js plan architecture-review \
  --repo /path/to/repo \
  --question "Is this architecture sound?"
node scripts/cw.js dispatch <run-id> --limit 6
node scripts/cw.js result <run-id> <task-id> /path/to/result.md
node scripts/cw.js status <run-id>
node scripts/cw.js graph <run-id>
node scripts/cw.js report <run-id> --show

A local folder (-dir PATH, from any directory) or a remote repository (--link <url>) can stand in for --repo. --link clones any git host — or downloads a .tar.gz/.zip archive — into a fail-closed, content-addressed cache, then reviews the checkout; cw clones list/gc manage that cache, and the MCP peers are cw_clones_list / cw_clones_gc. See Commands Or API.

Operator Commands

node scripts/cw.js worker summary <run-id>
node scripts/cw.js candidate summary <run-id>
node scripts/cw.js feedback summary <run-id>
node scripts/cw.js commit summary <run-id>
node scripts/cw.js multi-agent summary <run-id>
node scripts/cw.js blackboard summary <run-id>
node scripts/cw.js topology summary <run-id>
node scripts/cw.js state check <run-id>

Most human-facing summary commands also support JSON output with --json or --format json.

MCP Flow

MCP hosts can drive the same flow with JSON-first tools:

cw_app_run
-> cw_dispatch
-> cw_worker_manifest
-> cw_worker_output
-> cw_candidate_register
-> cw_candidate_score
-> cw_candidate_select
-> cw_commit
-> cw_operator_report

Topology tools include:

  • cw_topology_list
  • cw_topology_show
  • cw_topology_validate
  • cw_topology_apply
  • cw_topology_summary
  • cw_topology_graph

Multi-agent and blackboard tools expose the same runtime concepts that the CLI does. There should be no intentional CLI-only core behavior.

Schedules And Routines

node scripts/cw.js loop --intervalMinutes 30 --prompt "Continue this workflow."
node scripts/cw.js schedule create --kind loop --intervalMinutes 30 --prompt "Continue this workflow."
node scripts/cw.js schedule daemon --once
node scripts/cw.js routine create --kind github --prompt "Handle this GitHub event."
node scripts/cw.js routine fire github payload.json

Schedules and routines turn workflow continuation into explicit state instead of hidden host behavior.

Clone this wiki locally