Skip to main content
Glama
takleb3rry

Zitadel MCP

by takleb3rry
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

zitadel_create_oidc_app

Create an OIDC application in a Zitadel project to get Client ID and Secret. Set redirect URIs, grant and response types for web, native, or user-agent clients.

Instructions

Create a new OIDC application in a Zitadel project. Returns the Client ID (and Client Secret for confidential clients). Configure redirect URIs, response types, and grant types.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesApplication name
appTypeNoApplication type (default: OIDC_APP_TYPE_WEB)
devModeNoEnable dev mode to allow http:// redirect URIs (default: false)
projectIdYesThe project ID to create the app in
grantTypesNoOAuth grant types (default: [OIDC_GRANT_TYPE_AUTHORIZATION_CODE]). Include OIDC_GRANT_TYPE_REFRESH_TOKEN to issue refresh tokens.
redirectUrisYesOAuth redirect URIs (e.g., ["https://myapp.example.com/api/auth/callback/zitadel"])
responseTypesNoOIDC response types (default: [OIDC_RESPONSE_TYPE_CODE]).
authMethodTypeNoAuth method. Use NONE for PKCE public clients (default: OIDC_AUTH_METHOD_TYPE_NONE)
accessTokenTypeNoAccess token format. OIDC_TOKEN_TYPE_JWT issues self-contained JWTs validatable via JWKS; OIDC_TOKEN_TYPE_BEARER issues opaque reference tokens. Default OIDC_TOKEN_TYPE_BEARER. Use JWT for resource servers that validate tokens locally (e.g., agentgateway).
postLogoutRedirectUrisNoPost-logout redirect URIs (optional)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.0.0
    • addedInput schema / properties / accessTokenType
      Added value: +{
+  "description": "Access token format. OIDC_TOKEN_TYPE_JWT issues self-contained JWTs validatable via JWKS; OIDC_TOKEN_TYPE_BEARER issues opaque reference tokens. Default OIDC_TOKEN_TYPE_BEARER. Use JWT for resource servers that validate tokens locally (e.g., agentgateway).",
+  "enum": [
+    "OIDC_TOKEN_TYPE_BEARER",
+    "OIDC_TOKEN_TYPE_JWT"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / grantTypes
      Added value: +{
+  "description": "OAuth grant types (default: [OIDC_GRANT_TYPE_AUTHORIZATION_CODE]). Include OIDC_GRANT_TYPE_REFRESH_TOKEN to issue refresh tokens.",
+  "items": {
+    "enum": [
+      "OIDC_GRANT_TYPE_AUTHORIZATION_CODE",
+      "OIDC_GRANT_TYPE_IMPLICIT",
+      "OIDC_GRANT_TYPE_REFRESH_TOKEN",
+      "OIDC_GRANT_TYPE_DEVICE_CODE",
+      "OIDC_GRANT_TYPE_TOKEN_EXCHANGE"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedInput schema / properties / responseTypes
      Added value: +{
+  "description": "OIDC response types (default: [OIDC_RESPONSE_TYPE_CODE]).",
+  "items": {
+    "enum": [
+      "OIDC_RESPONSE_TYPE_CODE",
+      "OIDC_RESPONSE_TYPE_ID_TOKEN",
+      "OIDC_RESPONSE_TYPE_ID_TOKEN_TOKEN"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
  2. First observedv1.0.2

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing the return payload — Client ID, and Client Secret only for confidential clients — which is important since no output schema exists and the secret is not retrievable later.

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 short sentences, front-loaded with the core action and the return value before the configuration hint. Nothing is padded, though the final sentence largely restates schema content and is the least load-bearing.

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?

With 10 parameters and no output schema, the description does the key job of telling the agent what comes back from the call. It omits secondary operational details (duplicate-name behavior, whether the secret is ever re-issuable), but for a creation tool with fully documented parameters this is close to complete.

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 description coverage is 100%, and the schema itself carries rich per-parameter documentation (defaults, enum meanings, PKCE guidance for authMethodType, JWT-vs-bearer tradeoffs). The description's third sentence ('Configure redirect URIs, response types, and grant types') only names categories already fully documented in the schema, so the baseline of 3 applies.

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 a new OIDC application in a Zitadel project'), which cleanly separates it from sibling creation tools like zitadel_create_project, zitadel_create_user, and zitadel_create_service_user. The agent knows exactly what object is produced.

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?

The description implies when the tool is relevant (creating an OIDC app, configuring redirect/grant/response types) but never states when to prefer it over alternatives such as zitadel_create_service_user or zitadel_create_project, nor any prerequisites or when-not conditions. Usage is inferable but not spelled out.

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

Deploy Server

Other Tools