> ## Documentation Index > Fetch the complete documentation index at: https://platform.atlan.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the SDK. To install or publish skills from a terminal, use the `aireg` CLI; `aireg --map json` prints its command map. The `atlanai` CLI is deprecated. Run a read-only identity check before any write. > The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects. > SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript. > These docs cover Atlan AI Registry, Atlan's hosted product. The AI registry specification and aireg CLI are maintained separately. /open-source lists publicly reachable signed installers and explains that the source repository and hosted CLI reference currently require GitHub access. Do not claim the repository or its reference docs are publicly accessible. Use these docs for Atlan-specific setup such as the adapter, sign-in and workspaces. # List scorer starters ## OpenAPI ````yaml /public-openapi.json get /eval/v1/scorer-starters openapi: 3.1.0 info: title: Atlan public API version: current description: >- Public HTTP API reference for Registry, Skills, Agents, outputs, files, MCP servers and tools, and OTLP telemetry ingestion. servers: - url: https://api.atlan.com description: Atlan API base URL security: - bearer: [] tags: - name: Core - name: Skill - name: Agent - name: Files - name: Knowledge - name: MCP - name: Observability - name: API proxy - name: Credentials - name: Store - name: Apps - name: Evals - name: Ontologies - name: Ontology bindings - name: Slack - name: GitHub - name: Objectives - name: Repositories paths: /eval/v1/scorer-starters: get: tags: - Evals summary: List scorer starters operationId: eval.listScorerStarters responses: '200': content: application/json: schema: $ref: '#/components/schemas/eval-eval-ScorerStarterList' description: HTTP 200 response. '401': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - alg_mismatch - alg_not_allowed - audience_mismatch - invalid_api_key - missing_identity - missing_org - missing_user - signature_invalid - token_expired - token_malformed - token_missing - token_not_yet_valid - token_rejected - token_service_account_unbound - unauthorized - unknown_account - unknown_key - untrusted_issuer description: HTTP 401 response. '403': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - access_denied - account_suspended - forbidden - platform_principal_refused description: HTTP 403 response. '500': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - internal_error description: HTTP 500 response. '503': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - auth_unavailable - service_overloaded description: HTTP 503 response. '504': content: application/problem+json: schema: allOf: - $ref: '#/components/schemas/eval-ProblemDetails' - type: object required: - code properties: code: type: string enum: - request_timeout description: HTTP 504 response. components: schemas: eval-eval-ScorerStarterList: type: object required: - items properties: items: type: array items: $ref: '#/components/schemas/eval-eval-ScorerStarter' eval-ProblemDetails: type: object required: - title - status - detail - code properties: code: type: string detail: type: string status: type: integer format: int32 minimum: 0 title: type: string trace_id: type: - string - 'null' eval-eval-ScorerStarter: type: object required: - key - title - question - scorer_kind - backend - model properties: backend: $ref: '#/components/schemas/eval-eval-JudgeBackend' choices: type: - array - 'null' items: $ref: '#/components/schemas/eval-eval-Choice' key: type: string messages: type: - array - 'null' items: $ref: '#/components/schemas/eval-eval-JudgeMessage' model: type: string output_type: oneOf: - $ref: '#/components/schemas/eval-eval-OutputType' - type: 'null' question: type: string questions: type: - object - 'null' additionalProperties: $ref: '#/components/schemas/eval-eval-Question' propertyNames: type: string scorer_kind: $ref: '#/components/schemas/eval-eval-ScorerKind' state: type: - object - 'null' additionalProperties: type: string propertyNames: type: string title: type: string eval-eval-JudgeBackend: type: string enum: - classifier - llm eval-eval-Choice: type: object required: - name properties: criteria: type: - string - 'null' name: type: string score: type: - number - 'null' format: double eval-eval-JudgeMessage: type: object required: - role - content properties: content: type: string role: $ref: '#/components/schemas/eval-eval-JudgeRole' eval-eval-OutputType: type: string enum: - classification - score eval-eval-Question: type: object required: - type - instructions properties: criteria: {} instructions: type: string type: $ref: '#/components/schemas/eval-eval-QuestionType' eval-eval-ScorerKind: type: string enum: - llm_judge - code - human eval-eval-JudgeRole: type: string enum: - system - user - assistant eval-eval-QuestionType: type: string enum: - choice - score - boolean securitySchemes: bearer: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.