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

Filter tools

Filters

Showing 24 of 2662 tools.

Ranked tools

  1. #2041 · Plurio

    The AI agent that runs performance marketing on autopilot

    10Agent
  2. #2042 · Scribenote

    AI scribe that turns vet visits into SOAP notes in seconds

    10Agent
  3. AI-powered operating system for pharmacy that automates prior authorization, refill workflows

    10Agent
  4. #2044 · SoloAI

    AI music-creation platform that blends text-to-music generation with virtual artists and web3

    10Agent
  5. #2045 · Deemos

    Generative AI company whose Hyper3D Rodin platform creates high-quality 3D models from text or

    10Agent
  6. #2046 · ManaMind

    Autonomous AI agents that automate quality assurance in video games by playing them at scale

    10Agent
  7. #2047 · Bounti

    Autonomous AI teammate platform for sales, marketing, and customer success teams that performs

    10Agent
  8. #2048 · Conversion

    (formerly StyleAI) is a B2B marketing automation platform that uses AI to plan, build, and

    10Agent
  9. #2049 · Jenfi

    Singapore-based fintech offering revenue-based growth financing to digital-native small

    10Agent
  10. #2050 · Graphite

    AI-powered code review platform built around stacked pull requests, an automated merge queue

    10Agent
  11. #2051 · Nullify

    Offers an autonomous AI workforce for product security that scans code, triages

    10Agent
  12. #2052 · Speakeasy

    API tooling platform that automatically generates production-ready SDKs, documentation, and

    10Agent
  13. #2053 · Cassidy

    Context-powered AI automation platform that lets non-technical teams build and deploy AI

    10Agent
  14. #2054 · Bretton AI

    AI agent platform for financial crime and compliance operations, automating mission-critical

    10Agent
  15. 3D-printed rocket propellant and solid rocket motors for defense

    10Agent
  16. #2056 · Turion Space

    Space domain awareness and on-orbit imaging for space superiority

    10Agent
  17. #2057 · Rime

    Hyper-realistic, authentic-sounding AI voice models tuned for high-volume enterprise

    10Agent
  18. #2058 · Raspberry AI

    Generative AI platform for fashion creatives that accelerates apparel design from concept to

    10Agent
  19. #2059 · Beeble

    AI visual effects company whose SwitchLight technology relights people and scenes in photos

    10Agent
  20. #2060 · Bauplan

    Serverless, Python-first data platform that brings Git-style versioning and transactional

    10Agent
  21. #2061 · dltHub

    Company behind dlt, a popular open-source Python library for building data pipelines and

    10Agent
  22. #2062 · Pensive

    AI-assisted grading and personalized learning platform for higher education that automates

    10Agent
  23. #2063 · Edexia

    AI teaching assistant that grades essays and written assignments and can be trained and

    10Agent
  24. #2064 · Mitiga

    Cloud and SaaS threat detection, investigation, and response (TDIR) platform that helps SecOps

    10Agent

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.