Initialize DuckDB using a Tailpipe init SQL script, optionally specifying a new init script path.
AI agents invoke tailpipe_connect to trigger actions in Tailpipe. 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.
This tool initializes a DuckDB database engine by executing an SQL init script. Running database initialization scripts is an Execute-category action — it triggers external operations (database engine startup, script execution) whose effects depend on the script path argument. A malicious or misconfigured init script could execute arbitrary SQL, drop tables, or reconfigure the database, making the blast radius high.
From the tool's definition "Initialize DuckDB using a Tailpipe init SQL script, optionally specifying a new init script path"
Documented attack patterns abuse exactly the kind of access tailpipe_connect 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_connect:
{
"version": "1",
"default": "deny",
"tools": {
"tailpipe_connect": {
"limits": [
{
"counter": "tailpipe_connect_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}tailpipe_connect 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.
Free to start. No card required.
Initialize DuckDB using a Tailpipe init SQL script, optionally specifying a new init script path. It is categorised as a Execute tool in the Tailpipe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tailpipe MCP server in PolicyLayer and add a rule for tailpipe_connect: 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_connect 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 tailpipe_connect 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_connect. 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_connect 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.