# Scorecard

**Canonical:** https://apis.io/providers/scorecard/  
**Website:** https://www.scorecard.io/  
**APIs profiled:** 7

Scorecard is a simulation and evaluation platform for building, testing, and deploying frontier AI agents. Teams run their agents through thousands of realistic scenarios, judge outputs with configurable AI, human, and heuristic metrics, and ship new capabilities with confidence. The platform organizes work into Projects, Testsets, Testcases, Metrics, Runs, Records, Scores, and Systems, and exposes a REST API (bearer API keys prefixed ak_) plus official Python, TypeScript/Node, and Go SDKs, a hosted MCP server, tracing integrations for LangChain, the Vercel AI SDK, and the Claude Agent SDK, and a GitHub Actions integration for evals in CI. Scorecard was founded to solve AI agent evaluation at scale and is backed by Kindred Ventures.

## Kin Score — 54.9 / 100 (developing)

Scored 2026-08-17 under rubric 0.11.0. Trend: flat (+0.0 from 54.9).

| Facet | Score |
|---|---|
| Discoverability | 81.5 |
| Contract Quality | 62.0 |
| Governance | 11.5 |
| Operational Transparency | 36.8 |
| Developer Ergonomics | 64.7 |
| Commercial Clarity | 60.5 |

## Agent readiness — 57.4 (agent-native)

| Dimension | Value |
|---|---|
| Spec Presence | yes |
| Agentic Access | derived |
| MCP Server | yes |
| Auth Clarity | yes |
| Idempotency | verified |
| Error Semantics | documented |
| OpenAPI Examples | verified |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | derived |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## APIs (7)

- **Scorecard Metrics API** — The Metrics API from Scorecard — 1 operation(s) for metrics.
- **Scorecard Projects API** — The Projects API from Scorecard — 5 operation(s) for projects.
- **Scorecard Records API** — The Records API from Scorecard — 5 operation(s) for records.
- **Scorecard Runs API** — The Runs API from Scorecard — 2 operation(s) for runs.
- **Scorecard Systems API** — The Systems API from Scorecard — 3 operation(s) for systems.
- **Scorecard Testcases API** — The Testcases API from Scorecard — 2 operation(s) for testcases.
- **Scorecard Testsets API** — The Testsets API from Scorecard — 2 operation(s) for testsets.

## MCP servers (1)

- **scorecard-mcp.yml**

## Agentic access (1)

- **Scorecard Agentic Access** — 35 operations · 20 acting

## Security (3)

- **Scorecard Authentication** — http · 1 scheme
- **Scorecard Domain Security** — TLSv1.3 · HSTS · DMARC
- **Scorecard Trust Center** — SOC 2

## Tags

Company, AI, Agents, Evaluation, Testing, LLM, Observability, Simulation, Developer Tools, MCP

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/scorecard/). Scores are computed from the provider's own public artifacts under a published rubric.