AI agents call list_collections to retrieve information from Fathom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Listing collections retrieves metadata about available resources with no modification, deletion, or execution capabilities. This is a read-only discovery operation. Confidence is 0.85 rather than higher because the tool description is empty, requiring inference from the name and server context.
From the tool's definition Tool name 'list_collections' implies enumeration/listing of available document collections. Server context describes 'direct access to local document collections' and sibling tools include search and read operations typical of read-only access patterns.
Attacks that exploit this kind of access
list_collections. It is categorised as a Read tool in the Fathom MCP Server, which means it retrieves data without modifying state.
Register the Fathom MCP server in PolicyLayer and add a rule for list_collections: 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 Fathom. Nothing to install.
list_collections 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_collections 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_collections. 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_collections is provided by the Fathom MCP server (romanshnurov/fathom-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 →