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. #1609 · DOJO AI

    The agentic marketing operating system for challenger brands

    10Agent
  2. #1610 · Numa

    AI agents that answer every call and fill the service bay for dealerships

    10Agent
  3. #1611 · ComfyUI

    Open-source, node-based platform for building generative AI workflows for images and video

    10Agent
  4. #1612 · Tenzai

    AI-powered penetration testing platform that runs full, end-to-end pentests autonomously

    10Agent
  5. #1613 · Geordie

    Agent-native security and governance platform that gives enterprises control over their AI

    10Agent
  6. #1614 · Linkup

    Paris-based startup building a web search API architected specifically for AI systems and

    10Agent
  7. #1615 · Tofu (Hiring)

    Tofu is a candidate fraud and deepfake detection platform built for hiring and security teams

    10Agent
  8. #1616 · Holoworld AI

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

    10Agent
  9. #1617 · Cubby

    Collaborative research workspace that lets teams collect articles, PDFs, videos, and audio

    10Agent
  10. #1618 · ImagiPortal

    Create living AI personas that talk, call, and remember

    10Agent
  11. #1619 · Profet AI

    Taiwanese company providing a no-code AutoML platform built for manufacturing

    10Agent
  12. #1620 · Ctruh

    Bengaluru-based deep-tech startup building the infrastructure layer of the spatial internet

    10Agent
  13. #1621 · Neuronova

    Milan-based deep-tech startup developing ultra-low-power neuromorphic AI chips that let

    10Agent
  14. #1622 · Tabnine

    Private AI code assistant for enterprise developers.

    10Agent
    JavaScriptPython +7
  15. #1623 · Hebbia

    AI for the world's most demanding work

    10Agent
    API
  16. #1624 · Hightouch

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

    10Agent
  17. #1625 · Norm Ai

    Regulatory AI agents that turn rules into compliance automation

    10Agent
    API Webhooks OAuth2 python
  18. #1626 · Basis

    Autonomous AI agents built for accountants

    10Agent
  19. #1627 · Noon

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

    10Agent
  20. #1628 · Mozart AI

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

    10Agent
  21. #1629 · SpAItial

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

    10Agent
  22. #1630 · Alex

    Autonomous AI recruiter that interviews and screens job applicants

    10Agent
  23. #1631 · Lupa

    AI-native operating system for veterinary clinics.

    10Agent
  24. #1632 · Outmarket AI

    AI intelligence layer for insurance brokers and agencies

    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.