AI agents call get_howto_doc 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 appears to retrieve static documentation or instructional content from an indexed codebase. No modification, execution, or destructive capability is indicated. The empty description lowers confidence slightly, but the consistent pattern across sibling tools and the 'get_' prefix (classic Read pattern) justify Read classification with low severity.
From the tool's definition Tool name 'get_howto_doc' indicates retrieval of documentation or how-to guidance. Sibling tools (get_command_doc, get_doc_index, get_style_doc, explain_command, etc.) are all read-only documentation/discovery operations.
Attacks that exploit this kind of access
get_howto_doc. 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 get_howto_doc: 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.
get_howto_doc 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 get_howto_doc 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 get_howto_doc. 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.
get_howto_doc 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 →