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. #169 · Gemini CLI

    Google's free open-source terminal AI coding agent — 1M tokens, no cost

    60Agent
    MCP API OAuth2 typescript
  2. #170 · Persona

    Persona provides flexible and secure identity verification solutions for businesses to verify real people and real businesses online.

    60Agent
    JavaScriptiOS +3
  3. #171 · Replicate

    Run AI models in the cloud

    60Agent
    API PythonJavaScript
  4. #172 · fal

    Fastest generative-media inference for developers

    60Agent
    API Webhooks OAuth2 pythontypescript +2
  5. #173 · Weaviate

    Open-source AI-native vector database

    60Agent
    API PythonGo +3
  6. #174 · Factory

    The only software development agents that work everywhere you do, from IDE to CI/CD.

    60Agent
    CLI
  7. #175 · Arize AI

    The AI & Agent Engineering Platform for development, observability, and evaluation of LLM applications.

    60Agent
    Python
  8. #176 · Retell AI

    Hire your AI call center for sales, support, and appointment scheduling

    60Agent
    JavaScriptPython
  9. #177 · Aider

    AI pair programming in your terminal that edits your codebase and commits changes via Git.

    60Agent
    Python
  10. #178 · Skyfire

    The Agentic Commerce Platform for AI payments and identity verification.

    60Agent
  11. #179 · Vellum

    An AI Assistant that adapts to how you work, acts before you ask, and is entirely yours to customize.

    60Agent
    CLI
  12. #180 · Browserbase

    Browserbase makes the web as reliable and programmable as APIs for your AI agents.

    60Agent
    Python (Stagehand SDK)
  13. #181 · Picovoice

    The only all-in-one on-device voice AI platform already deployed at scale for enterprises.

    60Agent
    PythonNode.js +9
  14. #182 · Anchor

    Secure infrastructure for computer-use agents to automate any web task faster, cheaper, and more reliably.

    60Agent
    Python
  15. #183 · Algolia

    The AI search and retrieval platform for agentic, generative, and traditional search experiences.

    60Agent
    JavaScriptSwift +8
  16. #184 · Vercel AI SDK

    A unified TypeScript SDK for building AI apps with modern streaming, fallbacks, and multi-model support.

    60Agent
    TypeScriptJavaScript
  17. #185 · Cursor

    The AI code editor built for productive engineers.

    59Agent
    MCP API OAuth2
  18. #186 · Ara

    Voice-first computer use for Mac that lives in your notch.

    57Agent
    MCP API
  19. #187 · Lemma

    Reliability platform that catches AI agent regressions and auto-optimizes prompts in production.

    56Agent
    MCP API Webhooks
  20. #188 · Kueski

    Buy now, pay later and instant loans for Mexico, powered by AI

    55Agent
    API Webhooks
  21. #189 · Quo

    AI-driven business phone and front office for growing teams

    55Agent
    API Webhooks
  22. #190 · Bold

    Digital payments and financial tools for small and medium businesses in Colombia

    55Agent
    API Webhooks
  23. #191 · Teachable

    Create, market, and sell online courses and digital products

    55Agent
    API Webhooks
  24. #192 · Landbot

    No-code conversational chatbot builder for web and WhatsApp

    55Agent
    API Webhooks

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.