AI agents call recent_runs to retrieve information from Mcp Dagster without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical run information from Dagster without modifying, executing, or deleting any data or pipelines. It is a pure read operation that queries existing run metadata, similar to a list or get operation. The low severity reflects minimal blast radius—unauthorized access to run history could expose pipeline performance details but cannot trigger executions or alter infrastructure.
From the tool's definition Tool name 'recent_runs' and description 'Get recent Dagster runs' indicate a query/retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access recent_runs 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 recent_runs:
{
"version": "1",
"default": "deny",
"tools": {
"recent_runs": {}
}
}recent_runs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get recent Dagster runs. It is categorised as a Read tool in the Mcp Dagster MCP Server, which means it retrieves data without modifying state.
Register the Mcp Dagster MCP server in PolicyLayer and add a rule for recent_runs: 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.
recent_runs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the recent_runs 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 recent_runs. 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.
recent_runs 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.