AI agents call list_topic_suggestions to retrieve information from Peecai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns suggestions from the Peec AI API without creating, modifying, or deleting any data. It is a pure read operation with no side effects. The accept/reject actions are performed by separate tools (accept_topic_suggestion, delete operations), not this one.
From the tool's definition Tool name 'list_topic_suggestions' and description states it 'List[s] suggested topics' — a retrieval operation. The description clarifies suggestions 'can be accepted' or 'rejected' but the tool itself only lists/retrieves data without modifying state.
Attacks that exploit this kind of access
List suggested topics for a Peec AI project. Suggestions can be accepted to create topics or rejected to dismiss them. It is categorised as a Read tool in the Peecai MCP Server, which means it retrieves data without modifying state.
Register the Peecai MCP server in PolicyLayer and add a rule for list_topic_suggestions: 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 Peecai. Nothing to install.
list_topic_suggestions 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 list_topic_suggestions 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 list_topic_suggestions. 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.
list_topic_suggestions is provided by the Peecai MCP server (mcp-server-peecai). 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 →