AI agents call project_health to retrieve information from Tages without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves aggregated health metrics and diagnostic information about stored project memory. The action 'Get' and the read-only nature of querying health scores and improvement suggestions classify this as a Read operation. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal—an AI agent cannot cause harm by repeatedly calling this diagnostic tool.
From the tool's definition Tool name 'project_health' and description 'Get overall project memory health score' indicate a retrieval operation that queries and returns project metrics without modifying any data.
Attacks that exploit this kind of access
Get overall project memory health score with dimension breakdown and improvement suggestions. It is categorised as a Read tool in the Tages MCP Server, which means it retrieves data without modifying state.
Register the Tages MCP server in PolicyLayer and add a rule for project_health: 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 Tages. Nothing to install.
project_health 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 project_health 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 project_health. 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.
project_health is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →