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. #2185 · LiteLLM

    Open-source LLM gateway and Python SDK that lets developers call 100+ model providers using a

    10Agent
  2. #2186 · RagaAI

    AI testing and safety platform that automatically detects, diagnoses, and helps fix issues

    10Agent
  3. #2187 · Warp

    Agentic development environment born out of the terminal, rebuilt in Rust to give developers a

    10Agent
  4. #2188 · Love Companion AI

    Free AI girlfriend love simulator and romantic chat

    10Agent
  5. #2189 · Avoca AI

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

    10Agent
  6. #2190 · Chai Discovery

    Engineering better molecules using artificial intelligence for drug-like antibody design against challenging targets with atomic precision.

    10Agent
  7. #2191 · Blitzy

    The only autonomous code generation platform with infinite code context, building enterprise software in days, not months.

    10Agent
  8. #2192 · Higharc

    AI-powered connected homebuilding platform

    10Agent
    API rest
  9. #2193 · VoltaGrid

    VoltaGrid provides hybrid power solutions that reduce emissions, optimize energy loads, and lower costs for industrial applications and data centers.

    10Agent
  10. #2194 · Gestalt Diagnostics

    AI-enabled digital pathology platform for cancer diagnosis

    10Agent
  11. #2195 · Precision AI

    Autonomous drone swarms for plant-by-plant precision agriculture

    10Agent
  12. #2196 · Skej

    Autonomous AI scheduling assistant that works inside email, Slack, and SMS

    10Agent
  13. #2197 · Posha

    AI-powered countertop kitchen robot that cooks home meals automatically

    10Agent
  14. #2198 · Roamr

    Corporate travel home-sharing that pays employees, not hotels

    10Agent
  15. #2199 · Yellow Blue

    Context-aware AI document translation for professionals in 28 languages

    10Agent
  16. #2200 · Antiverse

    Generative AI antibody design for challenging and undruggable targets

    10Agent
  17. #2201 · Hormona

    Women's health company using AI and at-home testing to help women track, understand, and

    10Agent
  18. #2202 · Gravity Climate

    Enterprise carbon and energy management platform that helps industrial companies automate

    10Agent
  19. #2203 · Move AI

    Markerless motion-capture and 3D animation company that converts ordinary 2D video into

    10Agent
  20. #2204 · Ludus AI

    Generative AI toolkit that integrates directly with Unreal Engine to accelerate game

    10Agent
  21. #2205 · CrediLinq

    AI-powered B2B embedded finance platform that lets marketplaces, banks, and digital platforms

    10Agent
  22. #2206 · PredictAP

    AI-powered invoice coding and accounts payable automation platform built specifically for the

    10Agent
  23. #2207 · Dataglade

    AI-powered stock research platform that generates clear analyses and financial models for any

    10Agent
  24. #2208 · Amplemarket

    AI-powered sales copilot platform that unifies lead generation, data intelligence

    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.