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. #1945 · Lasso Security

    Cybersecurity platform purpose-built to secure generative AI, large language models, and AI

    10Agent
  2. #1946 · Rely

    AI-native diligence platform for multifamily real estate transactions

    10Agent
  3. #1947 · Ethosphere

    Voice-AI platform that turns in-store retail conversations into coaching insights for

    10Agent
  4. #1948 · DevRev

    AI-native platform that unifies customer support and software development on a single

    10Agent
  5. #1949 · AI Fantasy

    Character-first AI chat with persistent memory and image generation

    10Agent
  6. #1950 · RazrAi

    Uncensored AI image and video generation, privacy by default

    10Agent
  7. #1951 · Composer

    AI-native automated investing and algorithmic trading

    10Agent
    OAuth2
  8. #1952 · Aleph

    AI-native FP&A platform for modern finance teams

    10Agent
    API Webhooks OAuth2 rest
  9. #1953 · Elastics

    AI-native operating system for prediction markets - trade with words, not order forms.

    10Agent
  10. #1954 · Arzana

    AI automation for the manufacturing office — order entry, quoting, and customer updates.

    10Agent
  11. #1955 · AvatarOS

    Platform for high-end 3D AI virtual influencers with lifelike, expressive movement

    10Agent
  12. #1956 · Lucio

    AI-native workspace for lawyers to draft, research, and review

    10Agent
  13. #1957 · LatentForce

    Agentic AI for large-scale enterprise code migration and modernization

    10Agent
  14. #1958 · Trayd

    AI back-office operating system for specialty trade contractors

    10Agent
  15. #1959 · StormHarvester

    AI analytics that predict and prevent wastewater overflows and pollution

    10Agent
  16. #1960 · Kaaj

    Agentic AI credit intelligence that automates small-business loan underwriting

    10Agent
  17. #1961 · Presentations.AI

    AI-driven presentation platform that builds polished decks from prompts

    10Agent
  18. #1962 · LeanCon

    AI-powered pre-construction engineering team for contractors and developers

    10Agent
  19. #1963 · Homa

    AI homebuying platform that replaces the buyer's agent and rebates commission

    10Agent
  20. #1964 · Blockit

    AI scheduling agent that negotiates calendars on your behalf

    10Agent
  21. #1965 · Mixus

    AI agent command center built right inside your inbox and Slack

    10Agent
  22. #1966 · LakeFusion

    AI-native master data management on the Databricks Lakehouse

    10Agent
  23. #1967 · Q.ANT

    Photonic processors for energy-efficient AI and high-performance computing

    10Agent
  24. #1968 · Neurophos

    Metasurface optical processors for exaflop-scale AI inference

    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.