Assess the quality of a plan before execution. Scores against 8 criteria: clarity, scope, risks, testing, reversibility, impact, dependencies, timeline. Plans MUST score ≥80% to proceed.
AI agents call corn_plan_quality to retrieve information from CornMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only assessment/scoring of a plan against defined criteria. It produces a quality score but does not execute, modify, or delete anything. The enforcement of the ≥80% threshold is a gating check, not an action with side effects.
From the tool's definition 'Assess the quality of a plan before execution' and 'Scores against 8 criteria' — the tool evaluates/analyzes a plan and returns a score; no data is modified or deleted.
Documented attack patterns abuse exactly the kind of access corn_plan_quality gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CornMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for corn_plan_quality:
{
"version": "1",
"default": "deny",
"tools": {
"corn_plan_quality": {}
}
}corn_plan_quality is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Assess the quality of a plan before execution. Scores against 8 criteria: clarity, scope, risks, testing, reversibility, impact, dependencies, timeline. Plans MUST score ≥80% to proceed. It is categorised as a Read tool in the CornMCP MCP Server, which means it retrieves data without modifying state.
Register the Corn MCP server in PolicyLayer and add a rule for corn_plan_quality: 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 CornMCP. Nothing to install.
corn_plan_quality is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the corn_plan_quality 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 corn_plan_quality. 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.
corn_plan_quality is provided by the Corn MCP server (yuki-20/cornmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 CornMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 CornMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.