Unified apply primitive. Accepts a structured ReleaseSpec — database (migrations + expose), value-free secrets.require/delete declarations, functions, site, site.public_paths, subdomains, and routes.replace web routes — with explicit replace vs patch semantics per resource. Use site.public_paths ...
AI agents invoke deploy to trigger actions in Run402. 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 infrastructure-level operations that trigger external effects: database migrations run, functions deploy, web routes are modified, and subdomains are configured. These are code/configuration execution actions whose effects depend on the ReleaseSpec arguments provided. While it doesn't permanently delete data, it modifies live infrastructure and can affect service availability.
From the tool's definition Tool accepts ReleaseSpec with database migrations, function deployments, site configuration, routes, and subdomains.
Attacks that exploit this kind of access
Unified apply primitive. Accepts a structured ReleaseSpec — database (migrations + expose), value-free secrets.require/delete declarations, functions, site, site.public_paths, subdomains, and routes.replace web routes — with explicit replace vs patch semantics per resource. Use site.public_paths for clean static URLs such as /events backed by release asset events.html; explicit mode does not expose /events.html unless separately declared, while mode:. It is categorised as a Execute tool in the Run402 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Run402 MCP server in PolicyLayer and add a rule for deploy: 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 Run402. Nothing to install.
deploy 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 deploy 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 deploy. 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.
deploy is provided by the Run402 MCP server (kychee-com/run402). 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 →