request_deployment
Request that the Adrata control plane deploy a custom integration or extension. The manifest is validated locally first; the request is only sent if validation passes. Activation stays gated on policy review.
This record as markdown: /tools/adrata-starfield-mcp/request-deployment.md
What request_deployment does on Starfield
AI agents invoke request_deployment to trigger actions in Starfield. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
kind | string | Yes | What is being deployed |
path | string | — | Path to the manifest on disk |
notes | string | — | Notes shown to the reviewer |
target | string | — | Deployment target (default: adrata_hosted) |
manifest | object | — | Inline manifest JSON; takes precedence over path |
environment | string | — | Deployment environment. Production requires customer_runner or hybrid_runner. |
Parameters from the server's own tool schema.
Why request_deployment is rated High
request_deployment triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
The rule that runs request_deployment safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Starfield, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For request_deployment, this is the rule to start with:
request_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Starfield, apply this rule, and every request_deployment call is checked against it from then on.
Questions about request_deployment
Request that the Adrata control plane deploy a custom integration or extension. The manifest is validated locally first; the request is only sent if validation passes. Activation stays gated on policy review. It is categorised as a Execute tool in the Starfield MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
request_deployment accepts 6 parameters: kind, path, notes, target, manifest, environment. Required: kind. The full parameter table on this page comes from the server's own tool schema.
Register the Starfield MCP server in PolicyLayer and add a rule for request_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 Starfield. Nothing to install.
request_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 request_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 request_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.
request_deployment is provided by the Starfield MCP server (@adrata/starfield-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Starfield, and thousands of servers like it.
Across the catalogue