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. #1417 · Sense

    AI-powered talent engagement and recruiting automation platform that helps companies attract

    10Agent
  2. #1418 · Leena AI

    Agentic AI platform that delivers autonomous AI Colleagues for HR, IT, finance, and other

    10Agent
  3. #1419 · SeqOne Genomics

    Provides an AI-powered platform for next-generation sequencing analysis and clinical genomic

    10Agent
  4. #1420 · Cheehoo

    AI animation platform built to help studios and creators produce animated content faster and

    10Agent
  5. #1421 · Mindy

    Email-based AI personal assistant that you interact with simply by sending and CC'ing emails

    10Agent
  6. #1422 · Payman AI

    Agentic banking infrastructure that lets AI agents execute real financial transactions

    10Agent
  7. #1423 · Caspian

    AI-native customs compliance and global trade advisory platform that automates duty drawback

    10Agent
  8. #1424 · Wrtn

    (Wrtn Technologies) is a Seoul-based consumer AI platform that bundles multiple leading large

    10Agent
  9. #1425 · Gensmo

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

    10Agent
  10. #1426 · Rodin

    Rodin, by Deemos Technologies, is an AI 3D model generator that produces high-detail 3D assets

    10Agent
  11. #1427 · BidX

    AI PPC automation for Amazon and Walmart marketplace ads

    10Agent
    OAuth2
  12. #1428 · EleutherAI

    Non-profit open-source AI research lab behind GPT-J, GPT-NeoX, Pythia and The Pile

    10Agent
    Python
  13. #1429 · Axolotl AI

    The community-standard open-source framework for LLM fine-tuning and post-training

    10Agent
    Python
  14. #1430 · ModelBest

    Tsinghua-born unicorn behind the MiniCPM efficient edge AI models

    10Agent
    Python
  15. #1431 · Onlook

    The open-source 'Cursor for designers' — visually edit real React code with AI

    10Agent
    OAuth2
  16. Frontier AI research lab for visual intelligence, building production-grade image generation and editing models.

    10Agent
    API
  17. #1433 · Periodic Labs

    Creating AI scientists and autonomous laboratories to accelerate scientific discovery, starting with physical sciences.

    10Agent
  18. #1434 · Augment

    AI teammate that automates freight order-to-cash workflows

    10Agent
  19. #1435 · HavocAI

    Collaborative maritime autonomy for fleets of uncrewed surface vessels

    10Agent
  20. #1436 · Model ML

    AI workspace that automates investment banking and finance workflows

    10Agent
  21. #1437 · Boost.ai

    Enterprise conversational AI platform that automates customer service and support for highly

    10Agent
  22. #1438 · Delphi

    Lets experts and creators build a 'Digital Mind,' an interactive AI clone trained on their

    10Agent
  23. #1439 · Reflect

    AI-powered note-taking app designed to mirror the way you think, linking notes into a

    10Agent
  24. #1440 · Tracecat

    Open-source, AI-native security automation platform (SOAR) that gives security teams agents

    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.