Execute read-only SQL queries against cloud and security logs using DuckDB syntax. Results are returned in JSON format. Before writing queries, you can explore available tables and their structures using the tailpipe_table_list and tailpipe_table_show commands.
AI agents call tailpipe_query to retrieve information from Tailpipe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool executes SQL queries (which might suggest Execute category), the explicit read-only limitation means it only retrieves and queries data without side effects. Read-only queries cannot modify, delete, or create data structures. The blast radius of misuse is limited to information disclosure, making this a Read operation with low severity.
From the tool's definition Tool description explicitly states 'Execute read-only SQL queries' and 'Results are returned in JSON format.' The read-only constraint is the key differentiator.
Documented attack patterns abuse exactly the kind of access tailpipe_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tailpipe, and nothing reaches the server without passing your rules. This is the rule we recommend for tailpipe_query:
{
"version": "1",
"default": "deny",
"tools": {
"tailpipe_query": {}
}
}tailpipe_query is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute read-only SQL queries against cloud and security logs using DuckDB syntax. Results are returned in JSON format. Before writing queries, you can explore available tables and their structures using the tailpipe_table_list and tailpipe_table_show commands. It is categorised as a Read tool in the Tailpipe MCP Server, which means it retrieves data without modifying state.
Register the Tailpipe MCP server in PolicyLayer and add a rule for tailpipe_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 Tailpipe. Nothing to install.
tailpipe_query 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 tailpipe_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 tailpipe_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.
tailpipe_query is provided by the Tailpipe MCP server (turbot/tailpipe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tailpipe, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Tailpipe tools catalogued and risk-classified — across an index of 43,000+ MCP servers.