Submit a Spark job to run on a Lakehouse
AI agents invoke submit-spark-job to trigger actions in Fabric-Analytics-MCP. 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.
Submitting a Spark job executes arbitrary distributed computation on a Lakehouse. The effects are entirely determined by the job content: it could read, write, or delete data, run expensive computations, or alter infrastructure. This is clearly Execute-category with high severity due to the potential blast radius of arbitrary Spark code running at scale in a cloud data platform.
From the tool's definition 'Submit a Spark job to run on a Lakehouse' — submitting and running a Spark job triggers external computation whose effects depend on the job's code and arguments
Documented attack patterns abuse exactly the kind of access submit-spark-job gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fabric-Analytics-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for submit-spark-job:
{
"version": "1",
"default": "deny",
"tools": {
"submit-spark-job": {
"limits": [
{
"counter": "submit-spark-job_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}submit-spark-job 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.
Submit a Spark job to run on a Lakehouse. It is categorised as a Execute tool in the Fabric-Analytics-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Fabric-Analytics- MCP server in PolicyLayer and add a rule for submit-spark-job: 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 Fabric-Analytics-MCP. Nothing to install.
submit-spark-job 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 submit-spark-job 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 submit-spark-job. 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.
submit-spark-job is provided by the Fabric-Analytics- MCP server (santhoshravindran7/fabric-analytics-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 83 Fabric-Analytics-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
83 Fabric-Analytics-MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.