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
2443
With MCP
48
Public API
504
OAuth2
86
Avg score
21.7
✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filter tools

Filters

Showing 24 of 2443 tools.

Ranked tools

  1. #673 · WitnessAI

    AI safety and governance platform for the enterprise

    30Agent
    API Webhooks OAuth2 rest
  2. #674 · Sana Labs

    AI for organisational learning

    30Agent
    API
  3. #675 · Galileo AI

    The AI observability and eval engineering platform where offline evals become production guardrails.

    30Agent
  4. #676 · Joi AI

    Bootstrapped AI-companion app for chat, photos and voice with custom characters.

    30Agent
    API
  5. #677 · Anomalo

    The autonomous data system for the agentic enterprise, enabling self-driving data through AI-powered monitoring, investigation, and reporting.

    30Agent
  6. #678 · Podcastle

    Browser-based AI podcast studio with text-based editing.

    30Agent
    API
  7. #679 · EdgeCortix

    Energy-efficient AI processors purpose-built for edge generative AI

    30Agent
    API
  8. #680 · Sierra

    Conversational AI agents for every business

    29Agent
  9. #681 · PSI Quantum

    Photonic quantum computing for fault-tolerant AI workloads.

    26Agent
    API CUDA-Q
  10. #682 · Lemonade

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

    25Agent
  11. #683 · NEURA Robotics

    Cognitive and humanoid robots that work safely alongside people

    25Agent
  12. #684 · LimX Dynamics

    Full-size humanoid robots and embodied intelligence for the physical world

    25Agent
  13. #685 · EnCharge AI

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

    25Agent
  14. #686 · Gensyn

    Decentralized protocol for verifiable machine learning compute at scale

    25Agent
  15. #687 · Alloy

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

    25Agent
  16. #688 · Flexion Robotics

    The autonomy and intelligence stack powering humanoid robots

    25Agent
  17. #689 · Tana

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

    25Agent
  18. #690 · EngineAI

    Legged and humanoid robots powered by the SEED multimodal model

    25Agent
  19. #691 · Upstage AI

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

    25Agent
  20. #692 · CodeRabbit

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

    25Agent
  21. #693 · Coval

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

    25Agent
  22. #694 · Mobilint

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

    25Agent
  23. #695 · Fourier Intelligence

    General-purpose humanoid robots and embodied AI from rehabilitation roots

    25Agent
  24. #696 · DualBird

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

    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: MCP support (20pt), public API (20pt), webhooks (15pt), developer docs quality (15pt), SDK breadth (15pt), OAuth/auth completeness (15pt). Score is the weighted sum, rechecked weekly via automated scrapes.

›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.