AI agents call planning_status 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.
This tool retrieves and displays planning metadata without making any changes to data or triggering side effects. It is a straightforward information-gathering function analogous to 'get' or 'status' queries, which falls squarely into the Read category. Low severity because exposure of planning status poses minimal risk—it is informational only.
From the tool's definition Tool returns status information (goal, phases, decisions, errors, token count) for viewing/querying purposes. The description emphasizes retrieval ('Get compact planning status') with 'No auth needed', indicating a read-only query operation.
Attacks that exploit this kind of access
Get compact planning status: goal, phases, decisions, errors, token count. No auth needed. 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_status: 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_status 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_status 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_status. 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_status 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 →