Low Risk

pg_count_records

Count records in a table/view matching optional filters. Returns count using exact (precise but slower), planned (fast estimate from query planner), or estimated method.

Part of the Postgrest MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call pg_count_records to retrieve information from Postgrest without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though pg_count_records only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

postgrest.yaml
tools:
  pg_count_records:
    rules:
      - action: allow

See the full Postgrest policy for all 10 tools.

Tool Name pg_count_records
Category Read
Risk Level Low

View all 10 tools →

Agents calling read-class tools like pg_count_records have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the pg_count_records tool do? +

Count records in a table/view matching optional filters. Returns count using exact (precise but slower), planned (fast estimate from query planner), or estimated method.. It is categorised as a Read tool in the Postgrest MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on pg_count_records? +

Add a rule in your Intercept YAML policy under the tools section for pg_count_records. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Postgrest MCP server.

What risk level is pg_count_records? +

pg_count_records is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit pg_count_records? +

Yes. Add a rate_limit block to the pg_count_records rule in your Intercept 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.

How do I block pg_count_records completely? +

Set action: deny in the Intercept policy for pg_count_records. 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.

What MCP server provides pg_count_records? +

pg_count_records is provided by the Postgrest MCP server (@supabase/mcp-server-postgrest). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Postgrest

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.