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
2662
With MCP
80
Public API
646
OAuth2
148
Avg score
23

Filter tools

Filters

Showing 24 of 2662 tools.

Ranked tools

  1. #1729 · WyvernChat

    Free, unfiltered AI roleplay with thousands of characters

    10Agent
  2. #1730 · Rep AI

    Conversational AI sales concierge for Shopify brands

    10Agent
    API Webhooks OAuth2 rest
  3. #1731 · Pearl Health

    AI value-based care platform for primary care providers

    10Agent
    OAuth2
  4. #1732 · Basata

    AI that automates referrals, scheduling, and patient intake for specialty practices

    10Agent
  5. #1733 · Blossom Health

    AI copilot and operating system for psychiatry care

    10Agent
  6. #1734 · Worktrace AI

    AI that finds and ranks automation opportunities in your workflows

    10Agent
  7. #1735 · Perfect

    Agentic AI recruiter that sources and triages candidates

    10Agent
  8. #1736 · Optiml

    Real estate decision intelligence for portfolio-level strategy

    10Agent
  9. #1737 · qbiq

    AI that generates optimized floor plans, 3D tours and CAD models in minutes

    10Agent
  10. #1738 · Critical Loop

    Mobile microgrids that fast-track electric grid connections

    10Agent
  11. #1739 · Bone AI

    Mission-ready physical AI for defense and government

    10Agent
  12. #1740 · SigIQ.ai

    Personalized AI tutors that democratize elite exam preparation

    10Agent
  13. #1741 · StudyFetch

    AI study platform that turns class materials into learning tools

    10Agent
  14. #1742 · Flock AI

    AI-native visual commerce platform generating brand-accurate product imagery for fashion and retail

    10Agent
  15. #1743 · Nava

    Guardrails and validation for autonomous AI financial agents

    10Agent
  16. #1744 · Loman AI

    24/7 AI phone agent for restaurants that never misses a call

    10Agent
  17. #1745 · Superpower

    AI health super app with 100+ biomarker testing and a 24/7 AI health advisor

    10Agent
  18. #1746 · Iconic

    On-device, voice-driven AI for living, AI-native game worlds

    10Agent
  19. #1747 · MOA Foodtech

    AI-driven biomass fermentation turning food waste into sustainable proteins

    10Agent
  20. #1748 · Patlytics

    AI-native platform for the entire patent lifecycle, from drafting to infringement analysis.

    10Agent
  21. #1749 · Definely

    AI-powered contract drafting and review built into the lawyer's workflow.

    10Agent
  22. #1750 · Otto

    Autonomous AI travel agent for business travelers

    10Agent
  23. #1751 · BizTrip AI

    Agentic AI assistant for corporate travel without the search bar

    10Agent
  24. #1752 · Avallon

    AI agents that automate insurance claims operations

    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.