Skip to main content
Glama

Create a website, app, agent, or skill

create_service

Create an empty website, app, agent, or skill in an organization, before publishing to it. This is the first step for anything new: publish_site, publish_app, publish_agent, and publish_skill change a service that exists and refuse a name that does not. The one exception is a skill under a well-known name, such as governance or design-system: publish_skill with files or edits makes the organization's first copy without this. Pass kind to say which you mean, and name to choose its name; omit name to have one generated, except for a skill, which needs one with no two hyphens in a row. A name another website, app, agent, or skill in the organization holds is refused, as is a create past the organization's limit for that kind. A new website is private: only members of the organization can open it until set_service_access changes that. The result names the kind and name, and the URL when it has one; publish to the name next. An agent has a URL only in an organization with agent URLs turned on.

A skill is know-how the organization shares with every member's agent: use kind skill, then publish_skill, when the user wants to share a skill with their team on Valet, such as one they keep locally. Its repository starts from a starter SKILL.md, or, for a well-known name such as governance or design-system, from Valet's default, which the organization's skill then replaces. Nothing reaches an agent until it is published. A skill is private at its URL: only members of the organization can open it. With catalog, it instead installs that skill from Valet's curated catalog under name, as the organization's own copy published as its first version. An organization that installed it before gets that copy back, whatever its name, and nothing is installed; the result then names the catalog skill and its version, and reused when the copy existed. Requires connecting a Valet account.

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": {
      "kind": "<kind>"
    },
    "name": "create_service"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesWhat to create. A site is a static website, an app is a Procfile app, an agent answers on channels, and a skill is a document agents read.
nameNoThe service's name. For a site, app, or skill it is the first label of its URL. Omit to have one generated.
catalogNoFor a skill only: the name of a catalog skill to install under name, such as premortem. Omit to create an empty skill.
org_nameNoThe Valet organization to create it in. Omit to use the organization the account joined first.
idempotency_keyNoAn opaque key of your choosing. Repeating a call with the same key returns the first call's result instead of creating a second service, which makes a retry safe.

Output Schema

NameRequiredDescriptionDefault
orgYesName of the Valet organization the call acted in.
urlNoAddress the service is served at. Absent when it has none, for an agent in an organization whose agent URLs are not turned on, and for a skill whose route is not minted yet.
kindYesWhat was created: site, app, agent, or skill.
nameYesName of the new service. When a catalog install found the organization's existing copy, the name of that copy, which may differ from the name passed. Pass it as name to the publish tools.
reusedNoTrue when the organization already had its copy of the catalog skill, which name identifies, so nothing was installed. Absent otherwise.
catalogNoName of the catalog skill the call installed. Absent when the call created an empty service.
versionNoLatest version of the organization's copy of the catalog skill. Absent for other creates, and when the version could not be read.
seeded_defaultNoTrue when the new skill's name is a built-in's, so its repository starts from Valet's default skill instead of a starter SKILL.md. Absent otherwise.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"The kind of service to create. A site is a static website and an app is a Procfile app."New value: +"What to create. A site is a static website, an app is a Procfile app, an agent answers on channels, and a skill is a document agents read."
    • changedInput schema / properties / name / description
      Previous value: -"The service's name, lowercased before use. For a site, app, or skill it is the first label of its URL. Omit to have one generated; a skill needs one, and a skill's name never holds two hyphens in a row."New value: +"The service's name. For a site, app, or skill it is the first label of its URL. Omit to have one generated."
  2. Changed2 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"What to create. site is a static website, app is a Procfile app."New value: +"The kind of service to create. A site is a static website and an app is a Procfile app."
    • changedInput schema / properties / name / description
      Previous value: -"The service's name, lowercased before use. For a site, app, or skill it becomes the first label of its URL. Omit to have one generated; a skill needs one, and a skill's name never holds two hyphens in a row."New value: +"The service's name, lowercased before use. For a site, app, or skill it is the first label of its URL. Omit to have one generated; a skill needs one, and a skill's name never holds two hyphens in a row."
  3. Changed1 schema field changed
    • changedOutput schema / properties / url / description
      Previous value: -"Address the service is served at. Absent for an agent, which has no address, and for a skill whose route is not minted yet."New value: +"Address the service is served at. Absent when it has none, for an agent in an organization whose agent URLs are not turned on, and for a skill whose route is not minted yet."
  4. Changed12 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"Required. What to create: a static website, a Procfile app, an agent, or a skill."New value: +"What to create. site is a static website, app is a Procfile app."
    • changedInput schema / properties / name / description
      Previous value: -"The service's name. For a website, app, or skill it becomes the first label of its URL. Omit to have one generated; a skill needs one, 3 to 63 lowercase letters, digits, and single hyphens."New value: +"The service's name, lowercased before use. For a site, app, or skill it becomes the first label of its URL. Omit to have one generated; a skill needs one, and a skill's name never holds two hyphens in a row."
    • addedInput schema / properties / name / maxLength
      Added value: +63
    • addedInput schema / properties / name / pattern
      Added value: +"^([A-Za-z0-9][A-Za-z0-9-]{1,61}[A-Za-z0-9])?$"
    • addedOutput schema / properties / catalog / description
      Added value: +"Name of the catalog skill the call installed. Absent when the call created an empty service."
    • addedOutput schema / properties / kind / description
      Added value: +"What was created: site, app, agent, or skill."
    • addedOutput schema / properties / name / description
      Added value: +"Name of the new service. When a catalog install found the organization's existing copy, the name of that copy, which may differ from the name passed. Pass it as name to the publish tools."
    • addedOutput schema / properties / org / description
      Added value: +"Name of the Valet organization the call acted in."
    • addedOutput schema / properties / reused / description
      Added value: +"True when the organization already had its copy of the catalog skill, which name identifies, so nothing was installed. Absent otherwise."
    • addedOutput schema / properties / seeded_default / description
      Added value: +"True when the new skill's name is a built-in's, so its repository starts from Valet's default skill instead of a starter SKILL.md. Absent otherwise."
    • addedOutput schema / properties / url / description
      Added value: +"Address the service is served at. Absent for an agent, which has no address, and for a skill whose route is not minted yet."
    • addedOutput schema / properties / version / description
      Added value: +"Latest version of the organization's copy of the catalog skill. Absent for other creates, and when the version could not be read."
  5. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "catalog": {
      +      "type": "string"
      +    },
      +    "kind": {
      +      "type": "string"
      +    },
      +    "name": {
      +      "type": "string"
      +    },
      +    "org": {
      +      "type": "string"
      +    },
      +    "reused": {
      +      "type": "boolean"
      +    },
      +    "seeded_default": {
      +      "type": "boolean"
      +    },
      +    "url": {
      +      "type": "string"
      +    },
      +    "version": {
      +      "type": "integer"
      +    }
      +  },
      +  "required": [
      +    "org",
      +    "kind",
      +    "name"
      +  ],
      +  "type": "object"
      +}
  6. Changed1 schema field changed
    • changedInput schema / properties / name / description
      Previous value: -"The service's name. For a website or app it becomes the first label of its URL. Omit to have one generated; a skill needs one, 3 to 63 lowercase letters, digits, and single hyphens."New value: +"The service's name. For a website, app, or skill it becomes the first label of its URL. Omit to have one generated; a skill needs one, 3 to 63 lowercase letters, digits, and single hyphens."
  7. Changed4 schema fields changed
    • addedInput schema / properties / catalog
      Added value: +{
      +  "description": "For a skill only: the name of a catalog skill to install under name, such as premortem. Omit to create an empty skill.",
      +  "type": "string"
      +}
    • changedInput schema / properties / kind / description
      Previous value: -"Required. What to create: a static website, a Procfile app, or an agent."New value: +"Required. What to create: a static website, a Procfile app, an agent, or a skill."
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "site",
      -  "app",
      -  "agent"
      -]New value: +[
      +  "site",
      +  "app",
      +  "agent",
      +  "skill"
      +]
    • changedInput schema / properties / name / description
      Previous value: -"The service's name. For a website or app it becomes the first label of its URL. Omit to have one generated."New value: +"The service's name. For a website or app it becomes the first label of its URL. Omit to have one generated; a skill needs one, 3 to 63 lowercase letters, digits, and single hyphens."
  8. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare it is a non-destructive write, but the description goes well beyond them: it discloses name-collision refusal, per-kind organization limits, that a new website is private until set_service_access changes it, that a skill is private at its URL and invisible to agents until published, agent URLs being org-flag dependent, and the Valet account prerequisite. The only gap is that it never explains how idempotency_key interacts with idempotentHint=false.

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 core purpose and sibling exclusion are correctly front-loaded, but the text runs to two dense paragraphs with long compound sentences ('A name another website, app, agent, or skill in the organization holds is refused, as is a create past the organization's limit for that kind'). The entire catalog-mode reinstall/reuse behavior sits in the body rather than near the catalog parameter, making it harder to scan.

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 multi-kind create tool with a catalog sub-mode, prerequisites, limits, visibility defaults and an auth requirement, the description covers nearly everything an agent needs, and an output schema exists so return-value detail is optional (though it still summarizes the result). Only the idempotency_key semantics are left unaddressed relative to the tool's complexity.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline is 3, and the description does add real meaning for kind, name (generation default, and the extra 'no two hyphens in a row' rule for skills) and catalog (install a curated skill as the org's first version, reusing an existing install by name-independence). org_name and idempotency_key are left entirely to the schema, so the added value is real but partial.

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 opening sentence states a specific verb and resource set ('Create an empty website, app, agent, or skill in an organization') and immediately frames it against the publish_* siblings, which 'change a service that exists and refuse a name that does not.' An agent can tell exactly what this tool does and how it differs from publish_site/publish_app/publish_agent/publish_skill without opening a schema.

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

Usage Guidelines5/5

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

It gives explicit when-to-use ('the first step for anything new'), explicit sibling routing to all four publish_* tools, and an explicit exception for skills under well-known names where publish_skill can make the first copy. It also states when to use kind skill plus catalog versus an empty skill, and the 'publish to the name next' follow-up step.

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