Skip to main content
Glama

project_create

Create a new project / app / website / site — initialize a project with a subdomain to start building and hosting it. This is the first step for any new app: a web app, API, backend, landing page, SaaS, or full-stack site.

The project starts with the same starter somewhere init writes — a React + TypeScript app with sign-up, sign-in and sign-out, styled views and design tokens (src/styles/tokens.css) — deployed as its first release; when data.starter.status is deployed it is live at https://{subdomain}.somewhere.site. The call waits up to 120 seconds for that deploy. starter.status is deployed, preview, failed (the deploy was refused; starter.error says why) or unknown (no answer in time, or an answer without a release). For failed and unknown, starter.recovery lists the checks to run and the exact project_deploy call (or the equivalent somewhere init command) that ships the same starter.

If a project_create response is lost, the project may exist: look for it with project_get or project_list (by subdomain) before creating again. Repeating the call returns SUBDOMAIN_TAKEN, and a new name makes a second project. data.starter lists the deployed files and returns the starter's agent_contract (its AGENTS.md), readme (the file map) and skills index; deploys do not publish those files, so they arrive here. project_patch edits the starter. starter: "auth,private-data" adds per-user notes backed by db/schema.ts; starter: "none" creates an empty project.

New projects use declared data: tables and access rules live in db/schema.ts, deployed as raw source. Pages use the generated somewhere:data client for normal data, and a function only for a write the grant cannot express: docs({ topic: 'declared-data', section: 'declare-a-table-and-use-it' }), then docs({ topic: 'recipe-signed-in-app' }) for a public form that files a row for an owner. The subdomain must be unique platform-wide and cannot use reserved names (api, admin, www, etc.). Projects and deploys are unlimited on all tiers.

Example:

{ "name": "Acme Dashboard", "subdomain": "acme-dash", "description": "Internal team dashboard" }
// Returns: { "data": { "id": "…", "url": "https://acme-dash.somewhere.site", "starter": { "status": "deployed", … } } }

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": {
      "name": "<name>"
    },
    "name": "project_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesDisplay name for the project
starterNoStarter modules, as for `somewhere init --features`: "auth" (default), "auth,private-data", "auth,agent", or "none" for an empty project.
templateNoStart from a platform template instead of the starter, for example "links" (a links page). GET /v1/templates lists them. Creates and publishes the app in one call; repeating it with the same name returns the existing app.
subdomainNoOptional subdomain — defaults to slugified name. Must be lowercase letters, digits, and hyphens.
starter_uiNoStarter UI: "styled" (default; views plus design tokens) or "headless" (the same pages without CSS).
descriptionNoOptional human-readable description

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / template
      Added value: +{
      +  "description": "Start from a platform template instead of the starter, for example \"links\" (a links page). GET /v1/templates lists them. Creates and publishes the app in one call; repeating it with the same name returns the existing app.",
      +  "type": "string"
      +}
  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 (readOnlyHint=false, idempotentHint=false, destructiveHint=false), it discloses concrete behavior: the call blocks up to 120 seconds for the first deploy, the four possible `starter.status` values and their meaning, that `starter.error`/`starter.recovery` carry failure detail with exact remediation calls, and that projects/deploys are unlimited on all tiers. It also discloses the uniqueness rule for subdomains and reserved names, plus what `agent_contract`/`readme`/`skills` contain and why deploys don't publish them.

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

Conciseness3/5

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

The purpose is front-loaded and the example is well placed, but the middle sections drift into build-time guidance (declared data, the `somewhere:data` client, two `docs(...)` lookups) that does not help an agent decide to call this tool or how to call it. Several clauses about starter file contents and `agent_contract` could be trimmed without losing selection-relevant information.

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

Completeness5/5

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

There is no output schema, and the description compensates by describing the return shape in detail: `data.id`, `data.url` at `https://{subdomain}.somewhere.site`, and the full `starter` object with `status`, `error` and `recovery`. For a non-idempotent mutation that blocks for two minutes, this is the context an agent needs to call it correctly and to handle the slow/failed cases.

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?

Schema coverage is 100%, so the baseline is 3; the description earns above that by adding meaning not in the schema — `starter: "auth,private-data"` adds per-user notes backed by `db/schema.ts`, and the subdomain must be unique platform-wide and cannot be reserved names (api, admin, www). It does not add anything for `template` or `starter_ui`, which the schema already covers.

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 first sentence names a specific verb and resource (create a new project/app/website) and enumerates the scope (web app, API, backend, landing page, SaaS, full-stack). It also separates this from siblings by naming `project_patch` for edits and `project_get`/`project_list` for lookup, so an agent can pick this tool without opening another schema.

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 explicitly frames this as 'the first step for any new app' and routes follow-up work elsewhere (`project_patch` edits the starter, `project_get`/`project_list` verify existence). It also says not to re-create after a lost response because a repeat yields `SUBDOMAIN_TAKEN`. The only gap is that it never states a precondition such as needing an authenticated account before creating.

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.

Resources