Brand MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUTH_MODE | No | Set to `oidc` to enable the OAuth 2.1 resource-server auth flow (JWT validation against your IdP). | |
| EVAL_MODEL | No | Optional model override for the agent eval. | |
| OIDC_ISSUER | No | The IdP issuer URL used for JWT verification, e.g. https://login.microsoftonline.com/<tenant-id>/v2.0. Without it the server runs without auth for local development. | |
| ALLOWED_HOSTS | No | Host allow-list enforced for DNS-rebinding protection, e.g. `brand-mcp.example.com`. | |
| EVAL_MIN_PASS | No | Optional minimum pass threshold for the agent eval. | |
| OIDC_AUDIENCE | No | Allowed JWT audience(s), e.g. `<api-client-id>,api://brand-mcp`. | |
| MCP_PUBLIC_URL | No | Public URL of the MCP endpoint, e.g. https://brand-mcp.example.com/mcp, used in the WWW-Authenticate resource_metadata pointer. | |
| ALLOW_ANONYMOUS | No | Set to `true` to explicitly permit starting without auth in production. | |
| ANTHROPIC_API_KEY | No | API key required for the agent eval (`npm run eval:agent`). | |
| BROWSER_WS_ENDPOINT | No | A Playwright server endpoint for the browser-based check tools, for serverless platforms. | |
| BRAND_ROLES_REQUIRED | No | When `true`, a token without a brand app role sees no brands. | |
| BROWSER_CDP_ENDPOINT | No | A CDP browser service endpoint for the browser-based check tools. | |
| OIDC_REQUIRED_SCOPES | No | Scope the token must carry, e.g. `Brand.Read`; a missing scope returns 403 insufficient_scope. | |
| BRAND_CHECK_URL_HOSTS | No | Allow-listed `https://` hosts for live-URL checks; checks cannot reach any other host. | |
| OIDC_SCOPES_SUPPORTED | No | Scopes advertised in the protected-resource metadata, e.g. `api://brand-mcp/Brand.Read`. | |
| BRAND_CHECK_ASSET_HOSTS | No | Hosts rendered checks may load network assets from (Google Fonts by default); all other requests are blocked. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues