AI agents call percept_speakers 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 queries speaker metadata (identities, word counts, activity levels) without modifying data, executing code, or causing side effects. It is a straightforward data retrieval function. Severity is low because speaker lists are typically low-sensitivity metadata in a voice intelligence system, with minimal blast radius if an AI agent misuses it (e.g., listing speakers is not inherently harmful).
From the tool's definition Tool name is 'percept_speakers' and description states 'List all known speakers with word counts and activity.' The verb 'List' and the retrieval-only nature (no modification, deletion, or execution described) indicate a read operation.
Attacks that exploit this kind of access
List all known speakers with word counts and activity. 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_speakers: 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_speakers 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_speakers 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_speakers. 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_speakers 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 →