AI agents call list_formats 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.
The tool appears to enumerate available formats within the codebase discovery engine, a read-only operation with no side effects. The context of a 'capability discovery engine' and peer tools that all perform lookups or retrievals supports classification as Read. Confidence is slightly reduced due to the empty description, but the naming convention and server purpose provide sufficient evidence.
From the tool's definition Tool name 'list_formats' indicates a query/listing operation. The description is empty, limiting direct confirmation, but the naming pattern aligns with other sibling tools (get_command_doc, get_doc_index, get_howto, etc.) which are all read-only information…
Attacks that exploit this kind of access
list_formats. 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_formats: 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_formats 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_formats 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_formats. 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_formats 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 →