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
2668
With MCP
101
Public API
642
OAuth2
133
Avg score
22.9
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #217 · CopilotKit

    Open-source framework for building in-app AI copilots and agentic UIs

    55Agent
    API
  2. #218 · april

    Embedded, AI-powered tax filing and intelligence platform

    55Agent
    API
  3. #219 · Keycard

    Identity and access management built for AI agents

    55Agent
    API
  4. #220 · RadixArk

    Open infrastructure for frontier AI, built on SGLang

    55Agent
    API
  5. #221 · Alice & Bob

    Fault-tolerant quantum computing powered by self-correcting cat qubits.

    55Agent
    API
  6. #222 · Toku

    AI-powered recurring payments and collections for Latin America

    55Agent
    API
  7. #223 · Runloop

    Enterprise-grade cloud infrastructure and devboxes for AI coding agents

    55Agent
    API
  8. #224 · DRUID AI

    Enterprise agentic AI platform for conversational customer and employee service

    55Agent
    API
  9. #225 · FriendliAI

    Fast, cost-efficient generative AI inference for any model

    55Agent
    API
  10. #226 · Hyperbolic

    Open-access AI cloud for compute and inference

    55Agent
    API
  11. #227 · Portkey

    The control plane for production AI

    55Agent
    API
  12. #228 · TensorZero

    Open-source stack for building industrial-grade LLM applications

    55Agent
    API
  13. #229 · Chalk

    AI data platform delivering real-time context for models and agents

    55Agent
    API
  14. #230 · Turbopuffer

    Object-storage-native vector and full-text search at massive scale

    55Agent
    API
  15. #231 · Gentrace

    Collaborative testing and evaluation platform for generative AI apps

    55Agent
    API
  16. #232 · Cube

    The universal semantic layer for data and AI

    55Agent
    API
  17. #233 · Smallest.ai

    Fast, efficient real-time voice AI models and an agentic platform

    55Agent
    API
  18. #234 · Raindrop

    Sentry for AI agents — monitoring that catches silent failures in production

    55Agent
    API
  19. #235 · Unit21

    AI risk infrastructure for fraud and AML

    55Agent
    API
  20. #236 · Lamini

    Enterprise platform for tuning and running custom LLMs

    55Agent
    API
  21. #237 · Anvil Robotics

    Legos for robots: modular devkits to build and deploy physical AI fast

    55Agent
    API
  22. #238 · Bold

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

    55Agent
    API Webhooks
  23. #239 · Reactor

    Real-time AI video generation with near-zero time to first frame

    55Agent
    API
  24. #240 · Bits Technology

    Unified AI compliance infrastructure for AML and onboarding

    55Agent
    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.