AI agents invoke materialize_asset 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.
Materializing a Dagster asset executes the underlying computation (e.g., running transforms, writing to databases, updating data products). This is an Execute-category action because it triggers external operations whose effects depend on the asset and its dependencies. The blast radius is high because it can kick off expensive compute, modify downstream data products, or trigger cascading pipeline runs.
From the tool's definition "Materialize a specific Dagster asset" — materializing an asset triggers execution of pipeline/computation logic to produce or update the asset
Documented attack patterns abuse exactly the kind of access materialize_asset 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 materialize_asset:
{
"version": "1",
"default": "deny",
"tools": {
"materialize_asset": {
"limits": [
{
"counter": "materialize_asset_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}materialize_asset 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.
Materialize a specific Dagster asset. 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 materialize_asset: 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.
materialize_asset 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 materialize_asset 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 materialize_asset. 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.
materialize_asset 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.