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. #1321 · Waymo

    The world's most experienced autonomous driver

    11Agent
  2. #1322 · Chatbase

    Custom AI chatbots trained on your data.

    11Agent
    OAuth2
  3. #1323 · Corelayer

    AI on-call engineer that debugs alerts, logs, and data pipelines in regulated industries.

    11Agent
  4. #1324 · d-Matrix

    Digital in-memory compute (DIMC) chiplet-based hardware purpose-built for AI inference in the

    10Agent
  5. Maker of Dia, the AI-first browser that turns your tabs into a conversation

    10Agent
    OAuth2
  6. #1326 · Mythic

    Analog compute-in-memory chips for power-efficient edge AI

    10Agent
    Mythic SDK
  7. #1327 · Moonvalley

    Los Angeles-based AI research company building Marey, a production-grade generative video

    10Agent
  8. #1328 · Ayar Labs

    Optical I/O chiplets that replace electrical interfaces with light to move data in and out of

    10Agent
  9. #1329 · Loop

    Full-stack, verticalized AI platform for logistics and supply chains that ingests

    10Agent
  10. #1330 · Neural Concept

    Swiss CAD-native AI platform that brings deep-learning surrogate models and generative design

    10Agent
  11. Frontier research lab building a full-stack AI platform for semiconductor design, founded by

    10Agent
  12. #1332 · Crescendo

    AI-native contact center blending agents and humans

    10Agent
    API Webhooks OAuth2 pythontypescript
  13. #1333 · Upstage

    South Korean AI company best known for its Solar family of large language models and its

    10Agent
  14. #1334 · Ashby

    All-in-one, AI-powered recruiting platform that combines applicant tracking, sourcing, CRM

    10Agent
  15. AI drug-discovery company building generative and predictive models to design small-molecule

    10Agent
  16. #1336 · AIsphere

    Beijing-based company behind PixVerse, a fast-growing AI video generation platform for

    10Agent
  17. #1337 · Onyx

    Onyx, formerly Danswer, is an open-source enterprise AI search and assistant that connects to

    10Agent
  18. #1338 · Sema4.ai

    Offers a full-stack enterprise AI agent platform for automating mission-critical knowledge

    10Agent
  19. #1339 · Town

    A personalized AI assistant that acts like a chief of staff rather than a chatbot, learning

    10Agent
  20. #1340 · Fractile

    UK-based semiconductor startup building in-memory compute chips that radically accelerate

    10Agent
  21. #1341 · Nota AI

    Automatic AI model optimization for any device

    10Agent
    NetsPresso SDK
  22. #1342 · Genspark

    Your all-in-one AI workspace that puts busywork on autopilot.

    10Agent
  23. #1343 · Aqemia

    French AI drug-discovery company that fuses quantum-inspired statistical mechanics with deep

    10Agent
  24. #1344 · Emergence AI

    An enterprise-grade autonomous multi-agent orchestrator designed to coordinate AI 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.