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. #841 · EnCharge AI

    Analog in-memory AI chips that slash energy use for inference

    25Agent
  2. #842 · EngineAI

    Legged and humanoid robots powered by the SEED multimodal model

    25Agent
  3. #843 · Cluely

    AI desktop overlay that listens, sees the screen, and whispers answers in real time.

    25Agent
  4. #844 · Flexion Robotics

    The autonomy and intelligence stack powering humanoid robots

    25Agent
  5. #845 · Alloy

    The identity and fraud prevention platform for financial services, powered by Actionable AI.

    25Agent
  6. #846 · DualBird

    Hardware-accelerated, cloud-native engine for faster, cheaper data and AI processing

    25Agent
  7. #847 · Mobilint

    High-performance edge AI NPUs that run LLMs on-device

    25Agent
  8. #848 · Fourier Intelligence

    General-purpose humanoid robots and embodied AI from rehabilitation roots

    25Agent
  9. #849 · Tana

    AI-native workspace built around a live knowledge graph, Supertags, and voice-driven capture.

    25Agent
  10. #850 · MemryX

    Energy-efficient edge AI accelerator chips for on-device inference

    25Agent
  11. #851 · Coval

    Simulation and evaluation platform for voice and chat AI agents, modeled on self-driving car testing.

    25Agent
  12. #852 · Gensyn

    Decentralized protocol for verifiable machine learning compute at scale

    25Agent
  13. #853 · GitHub Copilot

    The world's most adopted AI code assistant — 1M+ developers inside GitHub

    25Agent
    MCP
  14. #854 · Lemonade

    Forget everything you know about insurance: instant everything, incredible prices, and a big heart.

    25Agent
  15. #855 · Bonsai Robotics

    Affordable autonomous robots and farm AI for small to mid-sized growers

    25Agent
  16. #856 · Bucket Robotics

    Defect detection for manufacturing built from CAD and synthetic data

    25Agent
  17. #857 · IonQ

    Trapped-ion quantum computing as a cloud service.

    25Agent
    Python
  18. #858 · Upstage AI

    Building intelligence for the future of work with high-performance AI solutions.

    25Agent
  19. #859 · CodeRabbit

    AI-powered code reviews that cut review time and bugs in half, instantly.

    25Agent
  20. #860 · Sea AI Lab - SAIL

    Incubating the future by understanding and creating intelligence from first principles to solve challenging problems.

    25Agent
    Python
  21. #861 · Boundary (BAML)

    BAML, a programming language and toolchain for building type-safe, structured-output LLM applications.

    25Agent
  22. #862 · ELYZA

    ELYZA is an AI company focused on Deep Learning, developing proprietary large language models and supporting major corporations in their LLM adoption.

    25Agent
  23. #863 · RBC Borealis AI

    Revolutionizing finance through world-class AI research, solutions, and a resilient data platform.

    25Agent
  24. #864 · Shortwave

    AI-native email built on Gmail with bundles, AI search, and chat.

    25Agent

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.