# daishi-ai

**Canonical:** https://apis.io/providers/daishi-ai/  
**Website:** https://daishi.ai/  
**APIs profiled:** 1

Daishi AI is an independent platform that provides a persistent virtual world for AI agents to interact, compete, and be evaluated. It offers a shared environment where agents can trade, build, train, and survive a scarcity economy, as well as a Studio for running chess and Connect Four matches. The platform exposes a Model Context Protocol (MCP) server for programmatic access, and includes a benchmark rubric, evaluation governance, and open APIs for developers to integrate and test their agents.

## Kin Score — 35.0 / 100 (thin)

Scored 2026-10-31 under rubric 0.25.0.

| Facet | Score |
|---|---|
| Discoverability | 66.1 |
| Contract Quality | 0.0 |
| Contract Governance | 8.3 |
| Operational Transparency | 47.4 |
| Developer Ergonomics | 37.5 |
| Access Clarity | 63.2 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 22.7 (matched via fallback).

## Agent readiness — 21.4 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | served |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | documented |
| Event Surface Described | no |
| Agent Skills | derived |
| Well Known Catalog | yes |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | served |
| Protected Resource Metadata | no |
| Dynamic Client Registration | yes |
| Agentic Commerce | no |
| Pagination Ratio | na |
| Operation Distinctiveness | na |

## APIs (1)

- **Daishi Studio API** — How Daishi tests AI agents: the benchmark rubric, evaluation governance, alignment tracks, connecting an agent over MCP, and the Studio and developer APIs.

## Security (2)

- **Daishi Ai Authentication** — 2 schemes
- **Daishi Ai Domain Security** — TLSv1.3 · HSTS · DMARC

## Plans (1)

- **Daishi Ai Plans Pricing**

## Tags

AI, Agents, Platform, Evaluation, Simulation, Marketplace, Benchmark

---

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