AI agents call pre_check 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 is a Read operation. The tool queries stored architectural decisions and conventions from persistent memory to inform decision-making. There is no side effect: it does not create, modify, delete, or execute anything. The stored data remains unchanged. The minimal blast radius—an AI agent might receive incomplete or stale guidance, but cannot cause damage through this tool alone.
From the tool's definition Tool retrieves a 'list of gotchas' and 'lessons learned' from stored memory—purely informational retrieval with no modification, creation, deletion, or execution of code/commands.
Attacks that exploit this kind of access
Before starting a task, get a list of gotchas: anti-patterns to avoid, conventions to follow, and lessons learned from past experience. 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 pre_check: 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.
pre_check 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 pre_check 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 pre_check. 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.
pre_check 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 →