AI agents call get_style_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.
No description provided, which lowers confidence slightly. However, the consistent naming pattern across the server (all 'get_*' tools appear to retrieve information from an indexed codebase) and the lack of any write/execute/delete semantics in the name indicate this is a safe read operation that queries documentation or style guide information without side effects.
From the tool's definition Tool name 'get_style_doc' follows the naming pattern of sibling tools like 'get_command_doc', 'get_doc_index', and 'get_howto_doc', all of which are read-only retrieval operations. The 'get_' prefix and '_doc' suffix strongly suggest documentation retrieval.
Attacks that exploit this kind of access
get_style_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_style_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_style_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_style_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_style_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_style_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 →