crow_pm_plan_decide
Record a human decision on a proposal: approved | rejected | cancelled. This is the chat gate — only call it when the human has explicitly decided. Approved events are exported to the feed on the next planner cron tick (or crow_pm_plan_export).
This record as markdown: /tools/kh0pper-crow/crow-pm-plan-decide.md
What crow_pm_plan_decide does on Crow
AI agents use crow_pm_plan_decide to create or update resources in Crow, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Crow environment.
Why crow_pm_plan_decide is rated Medium
This tool creates or modifies data reversibly by recording decision states and triggering exports to a feed. It does not delete data (so not Destructive), execute arbitrary code (so not Execute), move money (so not Financial), or merely retrieve data (so not Read).
From the tool's definition Tool records decisions (approved | rejected | cancelled) and exports approved events to a feed. The description explicitly states it performs record-keeping and export operations that modify state ("Record a human decision", "Approved events are exported").
Attacks that exploit this kind of access
The rule that runs crow_pm_plan_decide safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For crow_pm_plan_decide, this is the rule to start with:
crow_pm_plan_decide stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every crow_pm_plan_decide call is checked against it from then on.
Questions about crow_pm_plan_decide
Record a human decision on a proposal: approved | rejected | cancelled. This is the chat gate — only call it when the human has explicitly decided. Approved events are exported to the feed on the next planner cron tick (or crow_pm_plan_export). It is categorised as a Write tool in the Crow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Crow MCP server in PolicyLayer and add a rule for crow_pm_plan_decide: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Crow. Nothing to install.
crow_pm_plan_decide is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the crow_pm_plan_decide rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for crow_pm_plan_decide. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
crow_pm_plan_decide is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Crow, and thousands of servers like it.
This server
Across the catalogue