Start a new application run
AI agents invoke create_app_run to trigger actions in Dust 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.
The tool initiates execution of an application run, which is an active operation that triggers external computation or processes. Effects depend on the application being run and its arguments, making this an Execute category tool. Severity is high because misuse could trigger unintended application executions, consume resources, or cause unintended side effects depending on what the application does.
From the tool's definition "Start a new application run" - this triggers execution of an application/run process on the Dust platform
Attacks that exploit this kind of access
Start a new application run. It is categorised as a Execute tool in the Dust MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Dust MCP Server MCP server in PolicyLayer and add a rule for create_app_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 Dust MCP Server. Nothing to install.
create_app_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 create_app_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 create_app_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.
create_app_run is provided by the Dust MCP Server MCP server (ma3u/dust-mcp-server-postman-railway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →