Get the AI-generated summary for a specific meeting recording.
AI agents call get_summary to retrieve information from Fathom Video MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns pre-generated summary data without creating, modifying, deleting, or executing any operations. It has no side effects beyond returning existing information. The severity is low because summaries are typically non-sensitive outputs derived from existing meeting data, and retrieval poses minimal risk of misuse.
From the tool's definition Tool retrieves an AI-generated summary for a specific meeting recording. The description uses 'Get' which indicates data retrieval. No modification, deletion, or execution is described.
Attacks that exploit this kind of access
Get the AI-generated summary for a specific meeting recording. It is categorised as a Read tool in the Fathom Video MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Fathom Video MCP Server MCP server in PolicyLayer and add a rule for get_summary: 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 Video MCP Server. Nothing to install.
get_summary 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_summary 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_summary. 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_summary is provided by the Fathom Video MCP Server MCP server (trevorwelch/fathom-video-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 →