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. #1609 · TwinMind

    An AI second brain that captures your day and remembers everything

    10Agent
  2. #1610 · Bevel

    Your AI health companion that unifies wearables and bloodwork

    10Agent
  3. #1611 · Flai

    Omni-channel AI assistants that replace dealership phone trees

    10Agent
  4. #1612 · Hauler Hero

    The AI-powered operating system for waste management haulers

    10Agent
  5. #1613 · Gizmo

    Get addicted to learning with AI-generated quizzes and flashcards

    10Agent
  6. #1614 · Callosum

    Brain-inspired software that runs AI workloads on any mix of chips

    10Agent
  7. #1615 · Sandstone

    AI platform for in-house legal departments that turns institutional knowledge into agentic

    10Agent
  8. #1616 · Orbital Industries

    (formerly Orbital Materials) is an AI-industrial company that uses frontier AI to discover and

    10Agent
  9. #1617 · Kast

    Stablecoin-native financial platform that lets users store, earn, move, and spend digital

    10Agent
  10. #1618 · LawX

    Berlin-based legaltech startup building an AI-powered operating system for law firms and

    10Agent
  11. #1619 · Assort Health

    Specialty-specific generative AI voice agents that manage patient phone calls for medical

    10Agent
  12. #1620 · AethexAI

    Voice-AI company building the speech stack for emerging markets, with dialect-aware voice

    10Agent
  13. #1621 · MiChamba

    Mexican startup that turns WhatsApp into an operations platform for frontline teams, with an

    10Agent
  14. #1622 · Magie

    São Paulo-based AI fintech offering a financial assistant that lives inside WhatsApp

    10Agent
  15. #1623 · GetReal Security

    Enterprise deepfake defense and media forensics company that detects AI-generated

    10Agent
  16. #1624 · Ray Security

    AI-powered predictive data security platform that monitors how employees, systems, and AI

    10Agent
  17. #1625 · Sycamore

    Building a 'trusted agent operating system' for the enterprise, a full lifecycle platform to

    10Agent
  18. #1626 · Persona AI

    Houston-based humanoid robotics company building purpose-built humanoid robots for heavy

    10Agent
  19. #1627 · Zanskar

    Uses custom AI models and geoscience data to discover hidden geothermal energy resources and

    10Agent
  20. #1628 · Moonlake AI

    Multimodal reasoning models that let anyone generate entire interactive simulations and games

    10Agent
  21. #1629 · Maieutic Semiconductor

    Bengaluru deep-tech startup building a generative-AI-first platform for analog and

    10Agent
  22. #1630 · Stacks

    AI platform for enterprise accounting teams that automates operational finance workflows

    10Agent
  23. #1631 · Cohere Health

    Clinical intelligence company that uses AI to transform prior authorization and utilization

    10Agent
  24. #1632 · Synthflow

    Berlin-based no-code platform for building and deploying enterprise voice AI agents that

    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.