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

Filter tools

Filters

Showing 24 of 2668 tools.

Ranked tools

  1. #2593 · Tripo AI

    3D generation platform that turns text and images into production-ready 3D assets in seconds

    5Agent
  2. #2594 · Ontora

    AI agents that interview every employee to map how work actually gets done.

    5Agent
  3. #2595 · tl;dv

    AI meeting notetaker for Zoom, Google Meet, and Teams

    5Agent
  4. #2596 · Kiro

    Amazon's spec-driven AI IDE — build with PRDs, not prompts

    5Agent
  5. #2597 · Origin Financial

    All-in-one financial platform combining planning, investing, and money management.

    5Agent
  6. #2598 · Range

    AI-powered wealth management for high-earning households, flat-fee with human advisors.

    5Agent
  7. #2599 · Higharc

    AI-powered connected homebuilding platform

    5Agent
    API rest
  8. #2600 · Juno

    AI tax prep platform for SMB accounting firms that automates 90% of data entry across tax returns.

    5Agent
  9. #2601 · Cleo AI

    Sassy AI chatbot that nags, roasts, and coaches you into better money habits.

    5Agent
  10. Autonomous flight systems for type-certified cargo aircraft.

    5Agent
  11. #2603 · HrdWyr

    Bengaluru fabless semiconductor startup building AI-native chips for Physical AI and edge computing.

    5Agent
  12. #2604 · Danelfin

    AI stock selection platform that beat the S&P 500 by 74 percentage points since 2017.

    5Agent
  13. #2605 · flowscope

    AI-native consulting that maps and automates business processes in days, not months.

    5Agent
  14. #2606 · Boom AI

    AI agents that recover lost e-commerce revenue through personalized real-time conversations.

    5Agent
  15. #2607 · Replika

    AI companion who cares

    5Agent
  16. Democratizing personalized education globally through AI technology.

    5Agent
  17. #2609 · EdgeCortix

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

    5Agent
    API
  18. #2610 · Apptronik

    Building general-purpose humanoid robots to dramatically improve the way humans live and work.

    5Agent
  19. #2611 · Inbolt

    Real-time 3D vision and AI for industrial robot guidance

    5Agent
  20. #2612 · CrushOn AI

    Experience unfiltered, spicy AI character chat with no content restrictions.

    5Agent
  21. #2613 · Mind Robotics

    Building intelligent robotics for industrial deployment, starting with the factory floor.

    5Agent
  22. #2614 · Magic

    Building frontier code models to automate software engineering and research.

    5Agent
  23. #2615 · Imperagen

    Closed-loop, AI-guided enzyme engineering for improved and production-ready enzyme designs.

    5Agent
  24. Advancing responsible AI to help teachers meet the needs of every student through ethical, human-centered solutions.

    5Agent

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.