deploy
Pack the current project directory and deploy it to DenkOps, returning the live URL. No setup needed: if there is no denkops.json, one is inferred from the directory (name, slug, runtime) and written, creating a new project; if it exists, it deploys to that project. Auth uses DENKOPS_TOKEN (set b...
This record as markdown: /tools/denkopsai-mcp/deploy.md
What deploy does on Denkopsai
AI agents invoke deploy to trigger actions in Denkopsai. 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 |
|---|---|---|---|
dir | string | — | Directory to deploy (defaults to cwd) |
Parameters from the server's own tool schema.
Why deploy is rated High
The deploy tool executes a deployment operation that pushes code to an external platform (DenkOps) and makes it live. While not inherently destructive, it performs irreversible external operations (deployment) whose consequences depend on the code being deployed. This is Execute rather than Write because it invokes a deployment system with side effects beyond simple data modification.
From the tool's definition Tool description states it 'pack[s] the current project directory and deploy[s] it to DenkOps' and 'creates a new project' if one doesn't exist. This triggers external deployment operations whose effects depend on the project contents being deployed.
Risk signalsAccepts file system path (dir)
Attacks that exploit this kind of access
The rule that runs deploy safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Denkopsai, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For deploy, this is the rule to start with:
deploy 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 Denkopsai, apply this rule, and every deploy call is checked against it from then on.
Questions about deploy
Pack the current project directory and deploy it to DenkOps, returning the live URL. No setup needed: if there is no denkops.json, one is inferred from the directory (name, slug, runtime) and written, creating a new project; if it exists, it deploys to that project. Auth uses DENKOPS_TOKEN (set by the plugin) or denkops login. It is categorised as a Execute tool in the Denkopsai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
deploy accepts 1 parameter: dir. The full parameter table on this page comes from the server's own tool schema.
Register the Denkopsai 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 Denkopsai. 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 Denkopsai MCP server (@denkopsai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Denkopsai, and thousands of servers like it.
Across the catalogue