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. #385 · Pecan AI

    Predictive analytics platform with AI-generated SQL models.

    45Agent
  2. #386 · Cognism

    Premium B2B prospecting data with mobile numbers and intent signals.

    45Agent
  3. #387 · Recraft

    Brand-consistent AI image generation

    45Agent
    API Python
  4. #388 · Gemini Code Assist

    Google's AI code assistant — 1M token context, deeply integrated with Google Cloud

    45Agent
    VS Code ExtensionJetBrains Plugin
  5. #389 · Apollo.io

    AI-powered sales engagement platform with 275M+ contacts.

    45Agent
  6. #390 · EliseAI

    Conversational AI assistant for property management and leasing.

    45Agent
  7. #391 · Descript

    AI video and podcast editing — edit by editing the transcript.

    45Agent
  8. #392 · Standard AI

    Computer vision for autonomous checkout in physical retail.

    45Agent
  9. #393 · Twelve Labs

    Video understanding AI for developers

    45Agent
    API PythonJavaScript
  10. #394 · D-ID

    The leading digital human platform for AI-generated video creation and interactive agents.

    45Agent
  11. #395 · Bezi

    Project-aware AI development assistant for Unity game studios

    45Agent
    MCP
  12. #396 · Ambience Healthcare

    The AI operating system for healthcare

    45Agent
    API
  13. #397 · Read AI

    Your AI copilot transforming meetings, emails, and messages into summaries, insights, and instant answers.

    45Agent
  14. #398 · Kyutai

    An open-science AI lab dedicated to building and democratizing Artificial General Intelligence through open research.

    45Agent
    Python
  15. #399 · Phaidra

    AI agents for AI factories, optimizing complex power, cooling, and workload management systems to maximize tokens per watt.

    45Agent
  16. #400 · DeepSeek

    Open-weights frontier AI models with breakthrough efficiency.

    45Agent
    Python
  17. #401 · RamAIn

    Automate any UI task across legacy desktop, browser, and portal apps with natural language.

    45Agent
  18. #402 · Forethought

    AI for customer support automation

    45Agent
    API
  19. #403 · Truora

    Securely connect businesses and people, facilitating access to digital services and improving customer relationships.

    45Agent
  20. #404 · Superhuman

    The fastest email experience ever made, with AI triage and reply.

    45Agent
  21. #405 · QA Wolf

    AI-powered end-to-end test coverage with parallel execution.

    45Agent
  22. #406 · Reclaim.ai

    AI calendar that auto-schedules tasks, meetings, and habits.

    45Agent
  23. #407 · Regie.ai

    Generate more pipeline with the world's only AI Sales Engagement Platform for modern GTM.

    45Agent
  24. #408 · Gnani.ai

    Automate voice, SMS, WhatsApp, chat and email with AI agents that understand intent, trigger workflows, and close the loop.

    45Agent

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.