AI agents call planning_measure to retrieve information from Codecks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool tracks and reports token usage statistics for planning files. While 'snapshot' could imply writing data, the description emphasizes tracking and reporting metrics with no auth needed, suggesting read-oriented analytics. The most severe operation appears to be capturing a snapshot (possibly a write), but the overall purpose is monitoring/reporting.
From the tool's definition 'Track token usage of planning files over time' and operations 'snapshot, report, compare_templates' — primarily reporting/reading metrics
Attacks that exploit this kind of access
Track token usage of planning files over time. No auth needed. Operations: snapshot, report, compare_templates. It is categorised as a Read tool in the Codecks MCP Server, which means it retrieves data without modifying state.
Register the Codecks MCP server in PolicyLayer and add a rule for planning_measure: 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 Codecks. Nothing to install.
planning_measure 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 planning_measure 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 planning_measure. 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.
planning_measure is provided by the Codecks MCP server (rangogamedev/codecks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →