AI agents invoke launch_run to trigger actions in Mcp Dagster. 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 triggers external operations (job execution) whose effects depend on which job is selected and its configured logic. While the tool itself doesn't directly delete data or move money, launching unvetted or malicious Dagster jobs could perform destructive or financial operations.
From the tool's definition Tool name 'launch_run' and description 'Launch a Dagster job run' indicate execution of a predefined job/workflow. Dagster runs can perform arbitrary data processing, transformations, and side effects depending on the job configuration.
Documented attack patterns abuse exactly the kind of access launch_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Dagster, and nothing reaches the server without passing your rules. This is the rule we recommend for launch_run:
{
"version": "1",
"default": "deny",
"tools": {
"launch_run": {
"limits": [
{
"counter": "launch_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}launch_run 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.
Launch a Dagster job run. It is categorised as a Execute tool in the Mcp Dagster MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Dagster MCP server in PolicyLayer and add a rule for launch_run: 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 Mcp Dagster. Nothing to install.
launch_run 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 launch_run 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 launch_run. 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.
launch_run is provided by the Mcp Dagster MCP server (kyryl-opens-ml/mcp-server-dagster). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Dagster, 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.
9 Mcp Dagster tools catalogued and risk-classified — across an index of 43,000+ MCP servers.