Skip to main content
NeuronFeed

AI Agent Readiness Leaderboard

Which AI tools actually work with AI-agent workflows? We score every tool on 6 dimensions: MCP endpoint, public API, webhooks, developer docs, SDKs, and auth. Total out of 100. Automated weekly rechecks keep the scores current.

Scored
2668
With MCP
101
Public API
642
OAuth2
133
Avg score
22.9
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #1465 · Tabnine

    Private AI code assistant for enterprise developers.

    10Agent
    JavaScriptPython +7
  2. #1466 · Lindy

    Build AI assistants in minutes

    10Agent
    API
  3. #1467 · Hightouch

    Go from insight to live campaign in minutes – powered by all your data, brand knowledge, and AI.

    10Agent
  4. #1468 · Noon

    AI-native product design tool that closes the gap between design and code

    10Agent
  5. #1469 · Mozart AI

    A generative audio workstation putting artists at the center of AI music creation

    10Agent
  6. #1470 · SpAItial

    Spatial foundation models that generate full, coherent 3D environments from a prompt

    10Agent
  7. #1471 · Entire

    Developer platform for the era of agentic coding

    10Agent
  8. #1472 · Lupa

    AI-native operating system for veterinary clinics.

    10Agent
  9. #1473 · Outmarket AI

    AI intelligence layer for insurance brokers and agencies

    10Agent
  10. #1474 · Turing

    End-to-end AI for fully autonomous driving in Japan

    10Agent
  11. #1475 · Filed

    AI that automates the full lifecycle of tax returns

    10Agent
  12. #1476 · Reveal HealthTech

    Healthcare AI specialist building clinical trial and workflow automation products

    10Agent
  13. #1477 · Jack & Jill

    Conversational AI recruiters for job seekers and employers

    10Agent
  14. #1478 · Endra

    AI that automates mechanical, electrical, and plumbing design for buildings

    10Agent
  15. #1479 · All3

    AI architecture and construction robotics to triple building productivity

    10Agent
  16. #1480 · Luxury Presence

    AI-powered marketing and CRM platform for real estate agents

    10Agent
  17. #1481 · AfterQuery

    Expert reasoning datasets and benchmarks for frontier AI

    10Agent
  18. #1482 · Even Realities

    Camera-free smart glasses with a HUD display and AI assistant

    10Agent
  19. #1483 · Vuelo

    AI-native travel booking and payments platform

    10Agent
  20. #1484 · Harper

    AI-native commercial insurance brokerage for SMBs

    10Agent
  21. #1485 · Surf

    AI research model purpose-built for crypto and digital-asset intelligence

    10Agent
  22. #1486 · GridBeyond

    AI platform to manage distributed and flexible energy resources

    10Agent
  23. #1487 · Magma Math

    K-12 math platform where students show their thinking, powered by AI

    10Agent
  24. #1488 · Thoughtful AI

    Human-capable AI agents that automate healthcare revenue cycle management end to end

    10Agent

FAQ

›What is MCP?

Model Context Protocol — a standard introduced by Anthropic for AI agents to call external tools. Tools that ship MCP endpoints can be used by Claude, ChatGPT Desktop, Cursor, and others without custom plumbing.

›How is the agent-readiness score calculated?

Each tool gets 0-100 across 6 dimensions: public API (30pt), MCP server (25pt), webhooks (15pt), OAuth/delegated auth (10pt), machine-readable docs (10pt), and official SDKs (10pt). Score is the weighted sum, rechecked as profiles are re-enriched. Full reference: /docs/agent-readiness.

›How often are tools rechecked?

Daily for new tools, weekly for the existing leaderboard. Drift in MCP/API surface area is flagged for editorial review before the score updates.

›What counts as agent-ready?

We consider a tool agent-ready if it has at least 3 of: MCP endpoint, public API, webhooks, OAuth2, an SDK, and good docs. Score 60+ generally means an agent can integrate without source-code-level access.

›Why are some tools missing?

We score every published startup in the directory. Stealth-mode and pre-launch tools aren’t scored until they ship a public product.