run_query
Execute a read-only SELECT query and return structured rows (FR-003)
This record as markdown: /tools/allensandiego-postgres-mcp-server/run-query.md
What run_query does on Postgres
AI agents invoke run_query to trigger actions in Postgres. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
sql | string | Yes | Read-only SQL query to execute (e.g. SELECT) |
role | string | — | Optional PostgreSQL role to assume (SET ROLE) for this query only |
limit | integer | — | Maximum number of rows to return (capped by server maxRowLimit) |
offset | integer | — | Number of rows to skip before returning results |
params | array | — | Optional parameterized query values ($1, $2, etc.) |
Parameters from the server's own tool schema.
Why run_query is rated High
run_query triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAccepts freeform code/query input (sql)
Attacks that exploit this kind of access
The rule that runs run_query safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Postgres, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_query, this is the rule to start with:
run_query stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Postgres, apply this rule, and every run_query call is checked against it from then on.
Questions about run_query
Execute a read-only SELECT query and return structured rows (FR-003). It is categorised as a Execute tool in the Postgres MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
run_query accepts 5 parameters: sql, role, limit, offset, params. Required: sql. The full parameter table on this page comes from the server's own tool schema.
Register the Postgres MCP server in PolicyLayer and add a rule for run_query: 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.
run_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_query 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 run_query. 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.
run_query is provided by the Postgres MCP server (@allensandiego/postgres-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Postgres, and thousands of servers like it.
Across the catalogue