AI agents call list_howtos to retrieve information from Molmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about howto categories—a read-only operation with no side effects, state changes, or external operations. The context of a codebase discovery engine confirms this is a safe data lookup facility. No destructive, financial, or code execution elements are present.
From the tool's definition Tool name 'list_howtos' and description 'List howto categories with counts and descriptions' indicate a retrieval operation that queries and returns metadata about available howto resources without modifying any data.
Attacks that exploit this kind of access
List howto categories with counts and descriptions. It is categorised as a Read tool in the Molmcp MCP Server, which means it retrieves data without modifying state.
Register the Mol MCP server in PolicyLayer and add a rule for list_howtos: 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 Molmcp. Nothing to install.
list_howtos 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 list_howtos 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 list_howtos. 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.
list_howtos is provided by the Mol MCP server (molcrafts/molmcp). 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 →