Split.io

Fair

Agent Native Score

Free TierAPI Key AuthOpenAPI Spec

A feature management and experimentation platform that enables teams to safely deploy features, run A/B tests, and manage feature flags with real-time analytics and targeting capabilities.

Categories: Feature Management · Experimentation · Analytics

#5 of 6 in Feature Management · #6 of 7 in Experimentation · #56 of 117 in Analytics

Checklist Breakdown

13 of 33 checks passed. 14 unscored.

Discovery 63%

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 50%

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 100%

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 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 Not yet scored

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

Split.io has a documented REST API and sandbox environment, which supports agent tooling moderately well. However, it lacks an MCP server and llms.txt, limiting discoverability. Account creation requires human signup (no programmatic registration), and OAuth2 is the primary auth method without clear API key self-service flows, making autonomous agent onboarding difficult. The free tier and reliable infrastructure are strengths, but the platform is optimized for human teams rather than autonomous agents making real-time feature decisions.

Split.io

Let your agents find tools like Split.io