AI agents call percept_transcripts to retrieve information from Percept without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists existing conversation transcripts without creating, modifying, or deleting data. It falls clearly into the Read category. Severity is medium rather than low because transcripts may contain sensitive personal information, financial details, or confidential conversations captured by wearable microphones, presenting privacy and information disclosure risks if accessed by a compromised or…
From the tool's definition Tool description explicitly states 'List recent conversation transcripts' - a retrieval operation with no modification. The verb 'list' indicates a query-only action.
Attacks that exploit this kind of access
List recent conversation transcripts. It is categorised as a Read tool in the Percept MCP Server, which means it retrieves data without modifying state.
Register the Percept MCP server in PolicyLayer and add a rule for percept_transcripts: 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 Percept. Nothing to install.
percept_transcripts 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 percept_transcripts 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 percept_transcripts. 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.
percept_transcripts is provided by the Percept MCP server (getpercept). 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 →