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. #2041 · Credal

    Control plane that lets enterprises connect company data to LLMs and deploy secure AI

    10Agent
  2. #2042 · Aydi

    AI tools for global agriculture, anchored by Orth, an AI agronomy assistant for growers

    10Agent
  3. #2043 · Provision

    AI co-pilots for pre-construction estimating used by general contractors and trade

    10Agent
  4. #2044 · cubic

    AI-native code review platform, sometimes described as Cursor for code review, that catches

    10Agent
  5. #2045 · HeyMilo

    AI recruiter that uses voice AI agents to interview and evaluate candidates at scale for

    10Agent
  6. #2046 · Compa

    AI compensation intelligence platform that gives companies real-time market pay data and tools

    10Agent
  7. #2047 · Parspec

    AI-native software platform that helps construction product distributors and sales agents bid

    10Agent
  8. #2048 · Moreh

    South Korean AI infrastructure software company building a CUDA-like platform that runs AI

    10Agent
  9. #2049 · Toolpath

    Applied-AI CAM and estimating platform for machine shops that automates the most repetitive

    10Agent
  10. #2050 · Ohai.ai

    An AI household assistant from the founder of Care.com that tames family chaos

    10Agent
    OAuth2
  11. #2051 · Pixee

    Agentic AppSec platform that auto-triages and fixes code vulnerabilities

    10Agent
    OAuth2
  12. #2052 · Ranger

    AI QA engineer that writes, runs and maintains tests that find real bugs

    10Agent
    OAuth2
  13. #2053 · Onlook

    The open-source 'Cursor for designers' — visually edit real React code with AI

    10Agent
    OAuth2
  14. #2054 · 11x

    Digital workers that don't just automate tasks – they transform your business with human-like intelligence.

    10Agent
  15. #2055 · Avoca AI

    The AI Front Office for Home Services, providing always-on agents to answer calls, fill schedules, and streamline operations.

    10Agent
  16. #2056 · Cerebriu

    Real-time AI triage and protocol optimization for brain MRI

    10Agent
  17. #2057 · AVIAN

    Always-on AI thermal monitoring to prevent industrial fires and equipment failures

    10Agent
  18. #2058 · Manifest

    AI self-empowerment wellness app for Gen Z that gamifies emotional resilience

    10Agent
  19. #2059 · MarkeTeam.ai

    AI-native autonomous agents that work as a full marketing team

    10Agent
  20. #2060 · Howie

    AI scheduling assistant that lives in your inbox and books meetings for you

    10Agent
  21. #2061 · Single Origin

    AI-enhanced semantic layer that cuts redundant warehouse compute

    10Agent
  22. #2062 · TripSuite

    AI-powered business management software for travel agencies

    10Agent
  23. #2063 · PodUp

    All-in-one AI podcasting platform to create, grow, and monetize

    10Agent
  24. #2064 · Truleo

    AI agents for law enforcement: report writing, investigations, bodycam insights

    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.