AI agents invoke run_procedure to trigger actions in Komodo. 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 executes procedures whose effects depend on the procedure definition and arguments. It is not merely a read operation (no query/list semantics), nor a simple write (it actively runs/triggers operations rather than just storing data).
From the tool's definition Tool name 'run_procedure' and description 'Run a procedure' indicate execution of arbitrary operations. In the context of a DevOps platform managing servers, containers, stacks, and builds, procedures typically encapsulate complex workflows or shell commands.
Documented attack patterns abuse exactly the kind of access run_procedure gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Komodo, and nothing reaches the server without passing your rules. This is the rule we recommend for run_procedure:
{
"version": "1",
"default": "deny",
"tools": {
"run_procedure": {
"limits": [
{
"counter": "run_procedure_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_procedure 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.
Run a procedure. It is categorised as a Execute tool in the Komodo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Komodo MCP server in PolicyLayer and add a rule for run_procedure: 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 Komodo. Nothing to install.
run_procedure 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 run_procedure 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 run_procedure. 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.
run_procedure is provided by the Komodo MCP server (myrikld/komodo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Komodo, 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.
53 Komodo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.