AI agents invoke execute_flow to trigger actions in Kestra Python 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.
This tool triggers the execution of a Kestra workflow, which runs external operations whose effects depend on the workflow definition and arguments. This is a classic Execute category action—it initiates computation/operations that may have side effects. Severity is high because executing arbitrary workflows could consume resources, trigger external integrations, or perform unintended business logic.
From the tool's definition Tool name is 'execute_flow' and the server description indicates it 'enables AI assistants to interact with Kestra workflows through natural language, supporting operations like flow management, executions, backfills, and other Kestra features.' The tool…
Documented attack patterns abuse exactly the kind of access execute_flow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kestra Python MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_flow:
{
"version": "1",
"default": "deny",
"tools": {
"execute_flow": {
"limits": [
{
"counter": "execute_flow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_flow 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.
execute_flow. It is categorised as a Execute tool in the Kestra Python MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kestra Python MCP Server MCP server in PolicyLayer and add a rule for execute_flow: 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 Kestra Python MCP Server. Nothing to install.
execute_flow 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 execute_flow 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 execute_flow. 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.
execute_flow is provided by the Kestra Python MCP Server MCP server (kestra-io/mcp-server-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kestra Python MCP Server, 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.
39 Kestra Python MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.