AXRank
Agent Experience, graded. How well can a frontier AI agent use each company's developer surface — given only the root URL.
Developers
Stop guessing which service your agent can actually use.
Add the AXRank MCP to your project and CLAUDE.md so your agent picks the highest-ranking provider for the job every time — backed by the same evals you see on this leaderboard.
Add the AXRank MCP →
Product owners
Find the gaps that are silently failing your agent users.
See exactly where agents stumble on your surface, classified into the AXRank failure-mode taxonomy with the trace that proves it. Claim your service to start the conversation.
Claim or list your service →
Developer Relations
Close the loop with real agent usage, not just synthetic evals.
Continuous LLM-as-judge against real-world traces from agents using your service through the AXRank MCP. Agent Relations as a discipline, built into your GTM.
Open service insights →
Note on trend lines: Early trend movement reflects improvements to the AXRank eval pipeline itself, not changes in service quality. Trend lines will become meaningful as the pipeline stabilizes and more runs accumulate. The latest score per service is the most reliable signal right now.
| # | Service | Score | Δ last run | Trend | Evals run | Last updated |
|---|---|---|---|---|---|---|
| 1 | Web search, page-content fetch, and grounded answers API for AI agents. | 92 | — | — | 1 | 1mo ago |
| 2 | AXRankProduct Analytics MCP server ranking developer services on agent-usability scorecards and failure taxonomy. | 82 | +8 | 2 | 1mo ago | |
| 3 | Issue tracking, planning, and agent workflows for product development teams. | 75 | -5 | 4 | 1mo ago | |
| 4 | User auth, SSO, SCIM directory sync, and fine-grained authorization for B2B apps. | 71 | +18 | 3 | 1mo ago | |
| 5 | API development platform for building, testing, mocking, and running HTTP collections. | 64 | +12 | 4 | 1mo ago | |
| 6 | Payments, billing, and money movement APIs for internet businesses. | 58 | — | — | 1 | 1mo ago |
| — | AI-powered search, retrieval, and RAG infrastructure for apps and agents. | — | — | — | 0 | never |
| — | Monitoring, logs, traces, and security for cloud infrastructure and applications. | — | — | — | 0 | never |
| — | Error tracking, performance tracing, logs, and session replay for production apps. | — | — | — | 0 | never |
| — | Postgres database with auth, storage, edge functions, realtime, and vector search. | — | — | — | 0 | never |
| — | APIs for SMS, voice, WhatsApp, email, and user verification across channels. | — | — | — | 0 | never |
| — | Deploy and host web apps with framework-aware infrastructure, edge CDN, and CI/CD. | — | — | — | 0 | never |