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. #1633 · Mechanical Orchard

    Uses AI and reverse engineering to migrate large enterprises off legacy mainframe systems and

    10Agent
  2. #1634 · Holoworld AI

    Platform for creating AI-native characters and interactive video agents, anchored by Ava

    10Agent
  3. #1635 · Fastino

    Task-Specific Language Models (TLMs), compact models optimized for accuracy, speed, and cost

    10Agent
  4. #1636 · BackOps

    Building an AI-native operating system for global supply chain operations

    10Agent
  5. #1637 · Infinigence AI

    Chinese AI infrastructure startup that aggregates heterogeneous compute into a unified

    10Agent
  6. #1638 · Gensmo

    AI fashion agent that reinvents how people discover, style and shop for clothing

    10Agent
  7. #1639 · Generative Bionics

    Italian humanoid robotics company spun out of the Italian Institute of Technology (IIT)

    10Agent
  8. #1640 · Mercor

    Mercor is an AI-powered platform connecting top-tier remote AI talent with companies shaping the future of artificial intelligence.

    10Agent
  9. #1641 · Numeric

    AI accounting platform for finance teams

    10Agent
    API Webhooks OAuth2 rest
  10. #1642 · Notta

    AI transcription, meeting notes, and voice intelligence

    10Agent
    API Webhooks OAuth2 rest
  11. #1643 · Pearl Health

    AI value-based care platform for primary care providers

    10Agent
    OAuth2
  12. #1644 · Coval

    Simulation and evaluation platform for voice and chat AI agents, modeled on self-driving car testing.

    10Agent
  13. #1645 · Spur

    AI QA engineer that tests your website like a real user

    10Agent
  14. #1646 · qbiq

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

    10Agent
  15. #1647 · a2z Radiology AI

    An intelligence layer for medical imaging, starting with comprehensive CT triage

    10Agent
  16. #1648 · AdsGency AI

    Agentic AI ad agency that autonomously runs your entire paid marketing workflow

    10Agent
  17. #1649 · Synthetic

    Fully autonomous AI bookkeeping with no human bookkeepers

    10Agent
  18. #1650 · SuperDial

    AI voice agents that automate healthcare's endless administrative phone calls

    10Agent
  19. #1651 · Latent Technology

    Physics-driven generative AI animation that reacts in real time

    10Agent
  20. #1652 · Liminal

    AI tools that turn building your own RPG into a game

    10Agent
  21. #1653 · Dex

    AI talent agent matching elite AI and software engineers with hiring companies

    10Agent
  22. #1654 · Cambio

    Agentic AI platform for commercial real estate operations and compliance

    10Agent
  23. #1655 · Tidalwave

    Agentic AI for mortgage origination and borrower onboarding

    10Agent
  24. #1656 · Theo Ai

    Predictive AI that forecasts litigation outcomes and settlement values for legal teams.

    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.