Skip to main content
Glama

Create Clerk application

create_application

Create an application with a development instance in the connected workspace (like clerk apps create). Returns the new application_id, name, and instances with their publishable keys. Secret keys are removed, or returned as encrypted_secret_key when recipient_public_key is set.

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": "create_application"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesName for the application, shown in the Clerk Dashboard.
templateNoClerk template that pre-configures the application for a use case. Omit to create it with Clerk's default settings.
recipient_public_keyNoRSA public key to encrypt secret keys to: a JWK, or base64, base64url, or hex SubjectPublicKeyInfo DER, with a 2048 to 4096-bit modulus and exponent 65537. Each secret key then comes back as encrypted_secret_key, unpadded base64url RSA-OAEP ciphertext with SHA-256 for OAEP and MGF1 and an empty label, which only the matching private key can decrypt.

Output Schema

NameRequiredDescriptionDefault
nameYes
instancesYes
application_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / name / description
      Previous value: -"Application name."New value: +"Name for the application, shown in the Clerk Dashboard."
    • addedInput schema / properties / recipient_public_key
      Added value: +{
      +  "description": "RSA public key to encrypt secret keys to: a JWK, or base64, base64url, or hex SubjectPublicKeyInfo DER, with a 2048 to 4096-bit modulus and exponent 65537. Each secret key then comes back as encrypted_secret_key, unpadded base64url RSA-OAEP ciphertext with SHA-256 for OAEP and MGF1 and an empty label, which only the matching private key can decrypt.",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • changedInput schema / properties / template / description
      Previous value: -"Pre-configure the application from a Clerk template."New value: +"Clerk template that pre-configures the application for a use case. Omit to create it with Clerk's default settings."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "https://json-schema.org/draft/2020-12/schema",
      +  "additionalProperties": {},
      +  "properties": {
      +    "application_id": {
      +      "type": "string"
      +    },
      +    "instances": {
      +      "items": {
      +        "additionalProperties": {},
      +        "properties": {
      +          "environment_type": {
      +            "description": "\"development\" or \"production\".",
      +            "type": "string"
      +          },
      +          "instance_id": {
      +            "type": "string"
      +          },
      +          "publishable_key": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "instance_id",
      +          "environment_type"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "name": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "application_id",
      +    "name",
      +    "instances"
      +  ],
      +  "type": "object"
      +}
  2. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare it as a non-read-only, non-idempotent, non-destructive write, so the bar is lower. The description still adds real behavioral context: a development instance is created as a side effect, publishable keys come back, and secret keys are stripped or encrypted depending on `recipient_public_key`. It omits auth/permission requirements and any rate limits.

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

Conciseness5/5

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

Three sentences, front-loaded with what is created and where, followed by return-shape and the one conditional behavior. No redundant restatement of the name or title.

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 3-parameter mutation tool with full schema coverage, annotations, and an output schema, the description covers scope, output highlights, and the conditional secret-key behavior. It falls short only on operational context such as required permissions and what happens on duplicate names.

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 description coverage is 100%, so the baseline is 3. The description goes slightly beyond by linking `recipient_public_key` to the observable output change (secret keys removed versus returned as `encrypted_secret_key`), which ties the parameter to the call's effect rather than just its type.

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?

States a specific verb and resource ("Create an application") along with the scope that distinguishes it from siblings: a development instance in the connected workspace. The `clerk apps create` analogy and the contrast with create_production_instance / create_ios_application are clear 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 Guidelines3/5

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

Usage is implied: this is the tool to reach for when a new app is needed, and the schema notes that omitting `template` yields default settings. But there is no explicit when-not guidance, no mention of when to prefer create_production_instance versus this development-instance creation, and no stated prerequisites.

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