WHEN TO USE: To read the full verbatim LLM response for a specific monitoring result.
AI agents call lbm_get_transcript to retrieve information from LLM Brand Monitor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries monitoring results (transcripts of LLM responses) without altering, executing operations on, or destructively handling any data. It is a straightforward read operation with minimal security risk—appropriate for an AI agent to use in analyzing brand monitoring data.
From the tool's definition Tool name 'lbm_get_transcript' and description 'read the full verbatim LLM response' explicitly indicates retrieval of existing data with no modification, deletion, or side effects.
Attacks that exploit this kind of access
WHEN TO USE: To read the full verbatim LLM response for a specific monitoring result. It is categorised as a Read tool in the LLM Brand Monitor MCP Server, which means it retrieves data without modifying state.
Register the LLM Brand Monitor MCP server in PolicyLayer and add a rule for lbm_get_transcript: 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 LLM Brand Monitor. Nothing to install.
lbm_get_transcript 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 lbm_get_transcript 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 lbm_get_transcript. 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.
lbm_get_transcript is provided by the LLM Brand Monitor MCP server (@serpstat/llm-brand-monitor-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 →