Show currently-blocking sessions in a friendly tree (blocker → blocked) using pg_stat_activity ⨝ pg_blocking_pids(). Replaces the gnarly join an AI agent struggles to write. Returns each session
AI agents call find_blocking_queries to retrieve information from Postgres without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
find_blocking_queries retrieves and displays diagnostic information about blocking sessions in PostgreSQL. It queries system catalog views to present existing state as a formatted tree structure. This is purely observational with no side effects—it does not modify, execute arbitrary operations, delete data, or commit transactions.
From the tool's definition Tool description states it 'Show[s] currently-blocking sessions' using PostgreSQL system views (pg_stat_activity, pg_blocking_pids). No write, execute, delete, or financial keywords present. Returns data about active sessions.
Attacks that exploit this kind of access
Show currently-blocking sessions in a friendly tree (blocker → blocked) using pg_stat_activity ⨝ pg_blocking_pids(). Replaces the gnarly join an AI agent struggles to write. Returns each session. It is categorised as a Read tool in the Postgres MCP Server, which means it retrieves data without modifying state.
Register the Postgres MCP server in PolicyLayer and add a rule for find_blocking_queries: 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 Postgres. Nothing to install.
find_blocking_queries 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 find_blocking_queries 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 find_blocking_queries. 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.
find_blocking_queries is provided by the Postgres MCP server (teja-sudo/postgres-mcp-server). 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 →