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. #25 · Inkeep

    No-code platform to build trusted AI support agents from your knowledge

    90Agent
    MCP API
  2. #26 · Pillar Security

    The security platform for AI applications and agents

    90Agent
    MCP API
  3. #27 · Domo

    Business intelligence powered by AI

    90Agent
    API JavaScript
  4. #28 · Portia AI

    Open-source framework for controllable, reliable enterprise AI agents

    90Agent
    MCP API
  5. #29 · Morph

    Fast Apply infrastructure that merges AI code edits at 10,500 tokens/sec

    90Agent
    MCP API
  6. #30 · AgentPhone

    Phone numbers for AI agents — voice and messaging through one unified API.

    90Agent
    PythonNode.js
  7. #31 · Fireflies.ai

    AI meeting assistant

    90Agent
    API JavaScriptPython +1
  8. #32 · primitive

    Communication infrastructure that lets autonomous agents talk to humans and to each other.

    90Agent
    Node.jsPython +1
  9. #33 · Skyvern

    AI agents to automate workflows on any website, just like a human would.

    90Agent
    PythonTypeScript
  10. #34 · Apify

    Marketplace of thousands of Actors for web scraping, automation and live AI agent data

    90Agent
    MCP API Webhooks JavaScriptPython
  11. #35 · Raycast

    The extensible AI launcher that puts every app, command, and model a keystroke away

    85Agent
    MCP API OAuth2 TypeScriptReact
  12. #36 · Stainless

    Generates production-grade SDKs, docs and MCP servers from your OpenAPI spec

    85Agent
    MCP API OAuth2 TypeScriptPython +4
  13. #37 · HumanLayer

    AI coding IDE and context lab for teams

    85Agent
    MCP API OAuth2 PythonTypeScript
  14. #38 · Exa

    Search for AI applications

    85Agent
    API PythonJavaScript +1
  15. #39 · Skyflow

    Skyflow provides runtime AI data control, securing sensitive data across datastores, models, and AI agents.

    85Agent
    PythonJavaScript +1
  16. #40 · Coveo

    Coveo provides an AI Relevance™ Platform, offering AI-powered search and conversational discovery solutions built for enterprise ROI.

    85Agent
    JavaScriptPython +2
  17. #41 · Dosu

    Knowledge infrastructure for agents and humans, providing automatic knowledge capture without changing your workflow.

    85Agent
    Node.js
  18. #42 · E2B

    The Enterprise AI Agent Cloud provides open-source, secure environments with real-world tools for enterprise-grade AI agents.

    85Agent
    PythonJavaScript +1
  19. #43 · MeetGeek

    Agentic AI meeting assistant that records, transcribes and turns calls into automated action

    80Agent
    MCP API Webhooks
  20. #44 · Perplexity

    AI-powered answer engine delivering real-time, cited responses to complex queries.

    79Agent
    MCP API OAuth2 PythonNode.js
  21. #45 · HeyGen

    AI video platform with hyper-realistic avatars.

    79Agent
    MCP API OAuth2 cli
  22. #46 · Mistral AI

    Open and efficient foundation models

    78Agent
    MCP API OAuth2 PythonJavaScript +1
  23. #47 · Groq

    Fastest AI inference on the planet

    77Agent
    MCP API PythonJavaScript
  24. #48 · MiniMax

    Chinese AI lab behind Hailuo video and Talkie companions.

    76Agent
    MCP 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.