RunRL Agent Native Score | Agent Native Registry

Checklist Breakdown

0 of 33 checks passed.

This score can improve.

Get verified — we'll test your API hands-on and score all 33 checks. Most tools see a significant score increase.

Discovery 25%

Can an agent find and understand this tool without a web search?

— Published OpenAPI/Swagger spec

— Has llms.txt or llms-full.txt

— Has an MCP server (official or well-maintained)

— MCP server listed in a public registry

— API reference docs are publicly accessible

— Docs include runnable code examples

— Has a public changelog or release notes

— Has a public status page

Auth & Onboarding Not yet scored

Can an agent create an account and get credentials without human intervention?

— Signup does not require CAPTCHA

— Signup does not require phone verification

— Supports API key auth (not only OAuth)

— API key obtainable without manual approval

— No mandatory billing info to start

— Can sign up without creating an organization

Pricing Not yet scored

Can an agent operate autonomously without upfront payment or contracts?

— Has a free tier

— Usage-based pricing available

— No minimum contract or commitment

— Pricing page is public (no 'contact sales')

— Free tier sufficient for testing (not just a trial)

Agent Tooling Requires account Not yet scored

How well does the API work for non-human consumers?

— SDK available in 2+ languages

— Structured error responses (JSON with error codes)

— Idempotency support on write endpoints

— Pagination on list endpoints

— Webhook/event support

— Sandbox or test mode available

— Rate limit headers in responses

— Consistent REST resource naming

Reliability Requires account 35%

Does the tool fail gracefully when an agent makes a mistake?

— Meaningful error messages (not just 500)

— 429 responses include Retry-After header

— Documented uptime SLA (99.9%+)

— Graceful degradation under rate limits

— Request IDs in responses for debugging

— API versioning supported

Reviewer Notes

RunRL lacks foundational agent-native infrastructure—no MCP server, OpenAPI spec, or llms.txt file—making discoverability difficult for agents without manual setup. Account creation requires human interaction (email verification, CAPTCHA), preventing autonomous agent registration. While the platform supports API keys for programmatic access and offers a free tier with sandbox environment, documentation is sparse and API response structures are not well-documented for agent consumption. The core use case (RL infrastructure) is niche; agents would struggle to understand capabilities and integrate without extensive human guidance. Best suited for human-directed RL workflows rather than autonomous agent integration.

RunRL

Is this your tool?

Let your agents find tools like RunRL