Skip to main content
Glama

Create Source Deployment

nexusai_deploy_source
Destructive

Deploy from a Git repository, optionally a sub-folder (rootDir), to NEXUS AI managed infrastructure or a connected AWS, Google Cloud or Azure account. Can add or attach a database and sidecar services. Returns the deployment ID and status.

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": {
      "repoUrl": "<repoUrl>"
    },
    "name": "nexusai_deploy_source"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
regionNo
envVarsNoNon-secret configuration only. Configure passwords, API keys, tokens, and credential-bearing URLs in the authenticated NEXUS AI dashboard, never in chat.
repoUrlYesGit repository URL without embedded credentials. For private repositories, configure access in NEXUS AI and pass repoSecretName.
rootDirNoFolder inside the repo to deploy, e.g. "backend" or "apps/api". Use it for repos with separate frontend and backend apps; deploy each folder as its own deployment. Defaults to automatic detection from the repo root.
createDbNoProvision a managed cloud database paired with the deploy provider (Cloud Run→Cloud SQL, App Runner→RDS, Container Apps→Azure Database) and inject its connection env. Requires a cloud provider.
dbRegionNoCloud region for createDb (defaults to the deploy region).
memoryMbNoContainer RAM in MB for the NEXUS AI Docker provider. Defaults to 512. Values above 512 require the Pro plan or higher (up to 4096). Use it for apps that build or run in a memory-heavy way.
providerNodocker|gcp_cloud_run|aws_app_runner|azure_container_apps
servicesNoServices to attach at deploy time, matching the CLI's --services flag (e.g. ["postgresql","redis"]). On the docker provider these run as Docker sidecar containers with connection env (DATABASE_URL, REDIS_URL, etc.) auto-injected. On a cloud provider, a postgres/mysql entry is provisioned as a managed database instead (same as createDb); redis/mongodb are not supported on cloud providers.
frameworkNo
outputDirNo
requestIdNo
dockerfileNoDockerfile to use: raw contents, a repo-relative path (read after clone), or a GitHub file URL
repoBranchNo
environmentNoDeployment environment. Defaults to DEVELOPMENT.
managedDbIdNoAttach an existing managed database by ID instead of creating one. Its connection env (DATABASE_URL, etc.) is injected into the first deploy.
buildCommandNo
startCommandNo
installCommandNo
repoSecretNameNoOptional secret name containing private repo token.
dbEngineVersionNoEngine version for createDb (default: postgres 17 / mysql 8.0).
autoDestroyHoursNo
healthCheckEnabledNoSet to false to disable health checks. Defaults to true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / provider / description
      Previous value: -"docker|gcp_cloud_run|aws_ecs_fargate|azure_container_apps"New value: +"docker|gcp_cloud_run|aws_app_runner|azure_container_apps"
  2. Changed2 schema fields changed
    • addedInput schema / properties / envVars / description
      Added value: +"Non-secret configuration only. Configure passwords, API keys, tokens, and credential-bearing URLs in the authenticated NEXUS AI dashboard, never in chat."
    • changedInput schema / properties / repoUrl / description
      Previous value: -"Git repository URL."New value: +"Git repository URL without embedded credentials. For private repositories, configure access in NEXUS AI and pass repoSecretName."
  3. First observed

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnly=false, destructive=true, openWorld=true, so the mutation and blast-radius profile is partly covered. The description adds that it provisions infrastructure, can create databases and sidecars, and returns a deployment ID and status, but does not say that it is long-running provisioning, that it incurs cloud cost, or what the destructive hint actually means here.

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

Conciseness4/5

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

Three tightly written sentences with the capability stated first and no filler; the return-value note is the only mildly redundant element. Well front-loaded.

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

Completeness2/5

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

For a 24-param multi-cloud provisioning tool with a destructive hint, plan-tier constraints, and a confusable sibling (nexusai_deploy_create), the description is too thin: it omits prerequisites, provider/plan limits, and any differentiation, though it does cover the return shape.

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

Parameters2/5

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

With 24 parameters and 58% schema coverage, the description only touches rootDir, database attachment and sidecar services, leaving ten undocumented params (name, region, autoDestroyHours, buildCommand, startCommand, installCommand, framework, outputDir, requestId, repoBranch) unexplained in both description and schema. The description adds marginal meaning rather than compensating for the coverage gap.

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

Purpose4/5

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

A specific verb plus resource ('Deploy from a Git repository ... to NEXUS AI managed infrastructure or a connected cloud account') with the key affordances (rootDir, database, sidecars) named. However, it never distinguishes itself from the sibling nexusai_deploy_create, which an agent could plausibly reach for the same task.

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

Usage Guidelines2/5

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

The description states what it does but gives no when-to-use versus when-not guidance, no mention of the near-identical nexusai_deploy_create sibling, and no prerequisites (e.g. that createDb/services require a cloud provider). Usage must be inferred entirely from the capability sentence.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.