AI agents call comet_library to retrieve information from Comet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves historical research data from a library without creating, modifying, deleting, or executing any operations. It is a straightforward read operation with minimal security risk, as it only surfaces existing information already accessible to the user.
From the tool's definition Tool description states it 'Search[es] your Perplexity library for existing research. Returns past research threads matching your query.' The verb 'search' and 'returns' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Search your Perplexity library for existing research. Returns past research threads matching your query. It is categorised as a Read tool in the Comet MCP Server, which means it retrieves data without modifying state.
Register the Comet MCP server in PolicyLayer and add a rule for comet_library: 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 Comet. Nothing to install.
comet_library 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 comet_library 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 comet_library. 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.
comet_library is provided by the Comet MCP server (simplicianokelly52/comet_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 →