execute_read_query
Execute a read-only SQL query against a PlanetScale database
Part of the PlanetScale MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
WHEN AI AGENTS USE THIS TOOL
AI agents call execute_read_query to retrieve information from PlanetScale 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.
WHY ENFORCE A POLICY ON EXECUTE_READ_QUERY
Even though execute_read_query 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.
RECOMMENDED POLICY
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
execute_read_query:
rules:
- action: allowSee the full PlanetScale policy for all 5 tools.
DETAILS
MORE PLANETSCALE TOOLS
SIMILAR READ TOOLS ON OTHER SERVERS
list_bases Airtable list_tables Airtable list_records Airtable get_record Airtable search_records Airtable search Amplitude RELATED READING
FREQUENTLY ASKED QUESTIONS
What does the execute_read_query tool do?
Execute a read-only SQL query against a PlanetScale database. It is categorised as a Read tool in the PlanetScale MCP Server, which means it retrieves data without modifying state.
How do I enforce a policy on execute_read_query?
Add a rule in your Intercept YAML policy under the tools section for execute_read_query. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the PlanetScale MCP server.
What risk level is execute_read_query?
execute_read_query is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Can I rate-limit execute_read_query?
Yes. Add a rate_limit block to the execute_read_query 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 execute_read_query completely?
Set action: deny in the Intercept policy for execute_read_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.
What MCP server provides execute_read_query?
execute_read_query is provided by the PlanetScale MCP server (planetscale-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
ENFORCE POLICIES ON PLANETSCALE
Open source. One binary. Zero dependencies.