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. #553 · Diffuse Bio

    Generative AI for protein design with in-house assay development and data generation

    40Agent
    API
  2. #554 · AnySearch

    Real-time structured search infrastructure built for AI agents, not humans

    40Agent
    API
  3. #555 · BrowserAct

    Build a reusable web scraper from a single prompt, with browser infrastructure included

    40Agent
    API
  4. #556 · Actively AI

    Per-Account AI agents that run sales accounts 24/7 across the revenue org

    40Agent
    API
  5. #557 · Kargo

    AI camera towers that automate shipping and receiving at warehouse loading docks

    40Agent
    API
  6. #558 · Arcads

    Create winning AI video ads with 1,000+ AI actors in 35+ languages

    40Agent
    API
  7. #559 · Scrunch AI

    AI customer experience platform that optimizes brand visibility across AI search engines

    40Agent
    API
  8. #560 · Sola Security

    AI-driven no-code platform to build custom cybersecurity apps in minutes

    40Agent
    API
  9. #561 · GetVocal

    Governed conversational AI phone agents for regulated enterprises

    40Agent
    API
  10. #562 · Maki

    Conversational AI agents that run hiring end to end

    40Agent
    API
  11. #563 · Aethir

    Enterprise-grade decentralized GPU cloud for AI and gaming

    40Agent
    API
  12. #564 · Thunder Code

    AI-native software testing that anyone can run from the browser

    40Agent
    API
  13. #565 · Kognitos

    Neurosymbolic agentic automation that runs business operations in plain English

    40Agent
    API
  14. #566 · Unbox Robotics

    Swarm-robotics sortation operating system for warehouses and fulfillment

    40Agent
    API
  15. #567 · Sweet Security

    Unified runtime CNAPP for cloud and AI security

    40Agent
    API
  16. #568 · Juicebox

    AI recruiting agents and natural-language candidate search

    40Agent
    API
  17. #569 · Newo.ai

    AI receptionist handling voice, SMS, and WhatsApp for SMB front desks

    40Agent
    API
  18. #570 · Gradient AI

    AI risk analytics for underwriting and claims in insurance

    40Agent
    API
  19. #571 · Scowtt

    Predictive AI that turns unused CRM data into better performance ad campaigns

    40Agent
    API
  20. #572 · Lemon Slice

    Real-time AI avatars that turn any image into a live, conversational video call

    40Agent
    API
  21. #573 · Resistant AI

    AI-native fraud detection for documents and transactions, built to fight financial crime

    40Agent
    API
  22. #574 · Light

    AI-native finance platform automating accounting and bookkeeping

    40Agent
    API
  23. #575 · Salient

    AI voice agents handling borrower customer service for consumer lending

    40Agent
    API
  24. #576 · Cogent Security

    Autonomous AI agents for enterprise vulnerability management and remediation

    40Agent
    API

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.