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
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2662 tools.

Ranked tools

  1. #2089 · RentAHuman

    A marketplace where AI agents hire real humans on demand through an API or MCP endpoint.

    10Agent
  2. #2090 · Deep Interactions

    A collaborative AI app builder that lets entire teams ship production AI products together in an afternoon.

    10Agent
  3. #2091 · Tusk

    AI agent that generates unit and integration tests on every pull request

    10Agent
  4. #2092 · Aircapture

    Modular direct air capture delivering atmospheric CO2 as a commodity

    10Agent
  5. #2093 · Zing Coach

    AI personal trainer that builds adaptive workouts and tracks form from your phone

    10Agent
  6. #2094 · Magic Patterns

    AI design tool that turns prompts into production-ready UI for product teams

    10Agent
  7. #2095 · Visily

    AI UI design tool that turns text, sketches, and screenshots into editable mockups

    10Agent
  8. #2096 · Tandem

    AI-native office leasing marketplace and broker

    10Agent
  9. #2097 · Meet-Ting

    CC an AI assistant into email threads to schedule meetings instantly

    10Agent
  10. #2098 · Flank

    Autonomous, embedded AI legal agents that resolve legal and compliance requests in minutes.

    10Agent
  11. #2099 · 1Fort

    AI platform automating commercial insurance placement for brokers

    10Agent
  12. #2100 · Type

    The intelligent AI editor for storytellers and long-form writers

    10Agent
  13. #2101 · Biomatter

    Generative AI for protein and enzyme design across industries

    10Agent
  14. #2102 · Capalo AI

    AI-powered trading and optimization for grid-scale battery storage

    10Agent
  15. #2103 · suena energy

    AI trading autopilot for battery and renewable energy storage

    10Agent
  16. #2104 · Ello

    AI reading coach that listens to kids read aloud and helps them improve

    10Agent
  17. #2105 · finbar

    The AI investment analyst for hedge funds

    10Agent
  18. #2106 · Nowadays

    An AI copilot that automates corporate event and retreat planning

    10Agent
  19. #2107 · Punto Health

    London-based digital health company building an operating system for dementia care, using

    10Agent
  20. #2108 · Endel

    Sound-wellness company that uses AI to generate personalized, functional soundscapes designed

    10Agent
  21. #2109 · Glacier

    Affordable AI-powered recycling robots that sort materials at recovery facilities to boost

    10Agent
  22. #2110 · Circu Li-ion

    Luxembourg-based battery upcycling company using AI and advanced electrochemical techniques to

    10Agent
  23. #2111 · HULO

    Dutch watertech startup using AI to detect, size, and localize leaks in water distribution

    10Agent
  24. #2112 · Trata

    AI-powered research desk for hedge funds that uses AI agents to interview verified buy-side

    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.