Start a stopped deployment container.
AI agents invoke start_deployment 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.
Starting a container is an Execute operation because it triggers external computational work and establishes a running service whose effects cannot be fully predicted without knowing the container's image, entrypoints, and environment. While not Destructive (the operation is reversible by stopping the container), it clearly goes beyond Read/Write into active execution.
From the tool's definition Tool name and description indicate it 'Start[s] a stopped deployment container' — this initiates execution of a containerized workload whose behavior and side effects depend on the deployment's configuration and contents, which may be controlled or influenced…
Documented attack patterns abuse exactly the kind of access start_deployment 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 start_deployment:
{
"version": "1",
"default": "deny",
"tools": {
"start_deployment": {
"limits": [
{
"counter": "start_deployment_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_deployment 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.
Start a stopped deployment container. 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 start_deployment: 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.
start_deployment 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 start_deployment 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 start_deployment. 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.
start_deployment 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.