Generating code got cheap; verifying it didn't — you pay verification debt re-checking every AI "done". Planner makes "done" provable: the agent proves each acceptance criterion, an independent judge checks the evidence and accepts or rejects.
Overview
Planner — provable "done" for AI agents
Generating code got cheap. Verifying it didn't. Every time an AI agent says "done", someone re-checks it by hand — that's verification debt. Planner is a hosted MCP server that makes "done" provable instead of trusted.
How it works
- Decompose — break a goal into a tree of subtasks, one level at a time.
- Acceptance criteria — every node carries behavioral, objectively-checkable criteria (no "looks good to me").
- Evidence-gated done — a node can't close until real evidence is attached for each criterion, and an independent LLM judge checks that evidence and accepts or rejects it.
Why it's different
Most task MCP servers structure work and then mark it done on trust. Planner closes the loop: the agent proves each criterion; a judge verifies the proof. Task trackers tell you what to do — Planner tells you whether it was actually done.
Connect
Remote MCP endpoint (OAuth 2.1, DCR supported):
{
"mcpServers": {
"planner": {
"type": "http",
"url": "https://planner.monopoly-gold.com/_mcp"
}
}
}
Learn more: https://planner.monopoly-gold.com
Server Config
{
"mcpServers": {
"planner": {
"type": "http",
"url": "https://planner.monopoly-gold.com/_mcp"
}
}
}