Skip to main content
Glama

Create and deploy project

eurobase_create_project
Idempotent

Creates a project in a consented organization from a GitHub repository the account can access, attaches the repository and branch (the repository default branch when omitted) and starts its first deployment. Organization IDs are listed by eurobase_whoami. The project name becomes its hostname: 8-24 letters or digits, optionally separated by single hyphens. environment holds public (non-secret) values only and requires env:write; each entry names its targets: build (used only while the app is built), app (used by the running app; App deployments in the dashboard), or both. Secret values are added by the user in the Eurobase dashboard. A repository and branch already attached to another project is refused before any project is created. Returns once the deployment is accepted, before the build runs. The same idempotencyKey with the same input returns the same project and deployment and completes the steps an interrupted call did not finish; with different input it is refused.

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": {
      "organizationId": "<organizationId>",
      "name": "<name>",
      "repoFullName": "<repoFullName>",
      "idempotencyKey": "<idempotencyKey>"
    },
    "name": "eurobase_create_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
branchNo
environmentNo
repoFullNameYes
rootDirectoryNo
idempotencyKeyYes
organizationIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / environment / items / properties / targets
      Added value: +{
      +  "items": {
      +    "enum": [
      +      "build",
      +      "app"
      +    ],
      +    "type": "string"
      +  },
      +  "maxItems": 2,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • changedInput schema / properties / environment / items / required
      Previous value: -[
      -  "key",
      -  "value"
      -]New value: +[
      +  "key",
      +  "value",
      +  "targets"
      +]
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (non-destructive, idempotent, open-world), the description discloses non-obvious behavior: the default branch is used when omitted, the project name becomes the hostname with specific format constraints, environment entries must be public and declare build/app targets, secrets are out of scope, conflicting repository attachments are refused before creation, and the call returns after deployment acceptance but before the build runs. It also explains idempotency key semantics including interrupted-call recovery and input-mismatch refusal.

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?

The description is front-loaded with the core action and every sentence adds operational meaning; there is no filler. It is dense and unformatted as a single paragraph, which makes some details (environment targets, idempotency rules) harder to scan, but not verbose.

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

Completeness4/5

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

For a complex mutation with no output schema and no parameter descriptions, the definition covers prerequisites, side effects, refusal conditions, return timing, and idempotency thoroughly. The main remaining gap is the undocumented rootDirectory parameter and the absence of any indication of the returned project/deployment identifiers beyond the idempotency statement.

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

Parameters4/5

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

With 0% schema description coverage, the description compensates well for most parameters: it explains name/hostname rules, branch defaulting, organizationId sourcing from eurobase_whoami, environment privacy and target semantics, and idempotencyKey behavior. However, rootDirectory is never mentioned, leaving one of seven parameters undocumented in both schema and description.

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

Purpose5/5

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

The description opens with a precise verb and resource: 'Creates a project in a consented organization from a GitHub repository,' and adds scope details (attaches repository and branch, starts first deployment). This clearly distinguishes it from siblings like eurobase_get_project, eurobase_deploy, and eurobase_redeploy without requiring schema inspection.

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

Usage Guidelines4/5

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

It provides concrete prerequisites: organization IDs are listed by eurobase_whoami, the repository must be accessible, env:write is required for environment entries, and secrets must be added in the dashboard rather than here. It also states a refusal condition (repository/branch already attached elsewhere) and idempotency behavior. It does not explicitly name alternative tools for deploying an existing project, but the creation context is unambiguous.

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.