AI agents call guide to retrieve information from Tome without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to return usage documentation or help content, which is a read-only operation. Issue reporting could imply a Write action, but the description is vague. Given the context of a research library manager, this is most likely a help/documentation lookup. Confidence is moderate due to the uninformative description.
From the tool's definition "Usage guides and issue reporting" — retrieves guidance/documentation content with no apparent side effects
Attacks that exploit this kind of access
Usage guides and issue reporting. It is categorised as a Read tool in the Tome MCP Server, which means it retrieves data without modifying state.
Register the Tome MCP server in PolicyLayer and add a rule for guide: 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 Tome. Nothing to install.
guide 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 guide 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 guide. 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.
guide is provided by the Tome MCP server (retospect/tome-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 →