Create a scheduled job from a notebook
AI agents invoke create_job_from_notebook to trigger actions in SingleStore MCP Server. 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 creates a scheduled job that will repeatedly execute notebook code. While it involves creation (Write), the primary risk is that it triggers recurring code execution, which could run arbitrary database queries, scripts, or operations on a schedule. The Execute category is more severe and appropriate here due to the execution aspect of scheduled jobs.
From the tool's definition "Create a scheduled job from a notebook" — creates and schedules execution of notebook code
Documented attack patterns abuse exactly the kind of access create_job_from_notebook gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SingleStore MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_job_from_notebook:
{
"version": "1",
"default": "deny",
"tools": {
"create_job_from_notebook": {
"limits": [
{
"counter": "create_job_from_notebook_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} create_job_from_notebook 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.
Create a scheduled job from a notebook. It is categorised as a Execute tool in the SingleStore MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SingleStore MCP Server MCP server in PolicyLayer and add a rule for create_job_from_notebook: 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 SingleStore MCP Server. Nothing to install.
create_job_from_notebook 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 create_job_from_notebook 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 create_job_from_notebook. 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.
create_job_from_notebook is provided by the SingleStore MCP Server MCP server (singlestore-labs/mcp-server-singlestore). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 24 SingleStore MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
24 SingleStore MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.