AI agents call list_corpora to retrieve information from Pgmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or query knowledge base corpus information without side effects. The empty description prevents full confirmation, but the naming convention ('list_') is a strong indicator of a Read operation. Sibling tools like 'destroy_corpus', 'destroy_document', and 'delete' perform destructive operations, suggesting this tool is part of a read-only query family.
From the tool's definition Tool name 'list_corpora' indicates a listing/query operation with no parameters described that would suggest data modification. The 'list' verb and 'corpora' noun (plural of corpus, referring to knowledge base collections) indicate a retrieval operation.
Attacks that exploit this kind of access
list_corpora. It is categorised as a Read tool in the Pgmcp MCP Server, which means it retrieves data without modifying state.
Register the Pg MCP server in PolicyLayer and add a rule for list_corpora: 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 Pgmcp. Nothing to install.
list_corpora 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_corpora 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_corpora. 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_corpora is provided by the Pg MCP server (veloper/pgmcp). 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 →