AI agents call percept_conversations 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 data (conversations and their summaries) with no side effects. It is a passive read operation that does not create, modify, delete, or execute anything. The severity is low because listing conversation metadata poses minimal risk—it does not enable financial transactions, code execution, or data destruction.
From the tool's definition Tool name 'percept_conversations' and description 'List recent conversations with summaries' indicate a retrieval operation that queries existing conversation data without modification or execution.
Attacks that exploit this kind of access
List recent conversations with summaries. 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_conversations: 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_conversations 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_conversations 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_conversations. 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_conversations 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 →