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. #97 · Statsig

    The modern product development platform to measure what ships and ship what matters.

    70Agent
    ReactHTML +2
  2. #98 · Voiceflow

    Build, launch, and scale advanced AI agents for support, lead generation, and beyond without code.

    70Agent
    JavaScriptPython +1
  3. #99 · Speechmatics

    Speech APIs powering Voice AI with low-latency speech-to-text for multilingual, multi-speaker conversations.

    70Agent
    PythonJavaScript +1
  4. #100 · Armature

    Agent testing and observability for MCPs and CLIs across every model and harness.

    70Agent
  5. #101 · Eightfold AI

    Transforming the future of work with an AI-powered Talent Intelligence Platform for HR.

    70Agent
    PythonJavaScript +1
  6. #102 · ZoomInfo

    B2B contact and intent data with AI-powered prospecting.

    70Agent
    PythonJavaScript +1
  7. #103 · Anaplan

    Connected planning with AI-driven forecasting at enterprise scale.

    70Agent
    JavaPython +1
  8. #104 · LiveKit

    An open-source framework and developer platform for building, testing, deploying, scaling, and observing voice, video, and physical AI agents.

    70Agent
    PythonNode.js +3
  9. #105 · Inngest

    Orchestrate AI and backend workflows at any scale, making any code durable by default.

    70Agent
    TypeScript
  10. #106 · Vast.ai

    Agent-ready GPU infrastructure for AI, offering API-native provisioning, real-time pricing, and per-second billing.

    70Agent
    Python
  11. #107 · Temporal

    Build resilient applications with durable execution, ensuring code runs reliably even amidst distributed system failures.

    70Agent
    GoJava +6
  12. #108 · Cognition

    Applied AI lab building Devin, the AI software engineer.

    68Agent
    MCP API OAuth2
  13. #109 · Momentic

    AI-native automated software testing platform

    68Agent
    MCP API typescript
  14. #110 · Runway

    Applied AI research for video, image, and 3D.

    66Agent
    API Webhooks JavaScriptPython
  15. #111 · VAST Data

    Unifying software layer for AI infrastructure

    66Agent
    MCP API
  16. #112 · Scale AI

    Data labeling and AI infrastructure platform powering frontier models for enterprises and governments.

    66Agent
    API Webhooks OAuth2 Python
  17. #113 · Bria

    Licensed-data visual generative AI for enterprises

    66Agent
    API Webhooks OAuth2 pythontypescript
  18. #114 · Harvey

    The AI platform for elite law firms.

    65Agent
    MCP API
  19. #115 · Lovable

    The AI Fullstack Engineer that ships full-stack applications 20x faster than writing code

    65Agent
  20. #116 · Vanta

    Agentic trust and compliance automation platform

    65Agent
  21. #117 · Jasper

    AI copilot for enterprise marketing teams.

    65Agent
  22. #118 · DeepL

    AI solutions for accurate text, file, and voice translation, and business task automation.

    65Agent
    PythonJavaScript +2
  23. #119 · Pika

    AI-powered video generation and editing platform that turns text and images into dynamic videos.

    65Agent
    MCP API
  24. #120 · Stability AI

    Open models for image, video, audio, and 3D.

    65Agent
    PythonTypeScript +1

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.