Skip to main content
Glama
MCP Dokploy Online
by igoruam

ai-deploy

Idempotent

Deploy a Docker Compose application to a Dokploy environment using environment and application IDs, variables, and optional domains or config files.

Instructions

POST /ai.deploy

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "environmentId": "<environmentId>",
      "id": "<id>",
      "dockerCompose": "<dockerCompose>",
      "envVariables": "<envVariables>",
      "name": "<name>",
      "description": "<description>"
    },
    "name": "ai-deploy"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
nameYes
domainsNo
serverIdNo
configFilesNo
descriptionYes
envVariablesYes
dockerComposeYes
environmentIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

D1.3/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations only supply openWorldHint and idempotentHint, and the description adds nothing beyond that — it does not explain what actually happens during deployment, whether existing deployments are replaced or they accumulate, whether auth is needed, or how long it takes. With 6 required parameters and no structured hints, the description should carry the full burden, but it provides none.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is technically brief, but this is extreme under-specification, not conciseness: a single fragment with no sentence that conveys meaning beyond the endpoint path. There is nothing to front-load.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter mutation tool with unclear semantics and no output schema, the description is wholly inadequate. It supplies none of the behavioral or parameter context an agent needs in order to call this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 9 parameters, including required fields like environmentId, id, dockerCompose, envVariables, name, and description, plus nested domains and configFiles structure. The description does not explain any of them, so an agent gets no help with what 'id' identifies, what format envVariables takes, or how dockerCompose is used.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description is only "POST /ai.deploy", which restates the tool name as an HTTP verb plus endpoint rather than stating what the tool actually does. It never says that a deployment is created or what the AI deployment contains, so an agent cannot distinguish it from ai-create, ai-update, or the other deploy tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance appears at all, and the many sibling tools (ai-create, ai-update, ai-delete, application-deploy, compose-deploy) are never mentioned as alternatives or exclusions. The naming pattern alone gives no help for choosing among them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools