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

Public API

646

OAuth2

148

Avg score

✓ MCP support Public API Webhooks OAuth2 Python SDK TypeScript SDK

Filters

Showing 24 of 2662 tools.

#265 · Guardrails AI

The AI reliability platform for production GenAI

55Agent

API
#266 · Reality Defender

Real-time deepfake detection for enterprises, platforms, and governments

55Agent

API
#267 · Relace

AI models and infrastructure that power autonomous coding agents

55Agent

API
#268 · LGND

Geospatial embeddings that let AI agents understand satellite imagery

55Agent

API
#269 · Era

Software platform powering a new generation of AI gadgets and devices

55Agent

API
#270 · e6data

High-performance, format-neutral lakehouse compute engine

55Agent

API
#271 · Theoriq

Blockchain protocol for collectives of autonomous on-chain AI agents

55Agent

API
#272 · Almanak

AI agent framework for building and deploying DeFi trading strategies

55Agent

API
#273 · OatFi

API-first embedded credit network for B2B payments

55Agent

API
#274 · BentoML

Unified inference platform to run AI at scale

55Agent

API
#275 · Kintsugi

Voice biomarker AI to detect depression and anxiety from speech

55Agent

API
#276 · Granica

AI data platform for safe, efficient training data — privacy, classification, and cost reduction

55Agent

API
#277 · Vectorize

Turn unstructured data into AI-ready vectors for RAG pipelines

55Agent

API
#278 · Curacel

AI insurance infrastructure for emerging markets

55Agent

API
#279 · Nava

Escrow and verification layer that keeps AI financial agents in check

55Agent

API
#280 · OpenObserve

AI-native, open-source observability for logs, metrics, and traces

55Agent

API
#281 · CUDIS

Web3 and AI-powered smart ring with a personal health coach

55Agent

API
#282 · Vana

Decentralized network for user-owned data to train AI models

55Agent

API
#283 · Palabra AI

Real-time AI voice translation that replaces interpreters

55Agent

API
#284 · Synthesized

AI that automates software testing and test-data generation for the AI era

55Agent

API
#285 · Sloyd

AI 3D model generation with parametric control for game makers

55Agent

API
#286 · Nexad

The ad network for AI-native advertising in chatbots

55Agent

API
#287 · Sieve

AI video APIs for understanding, dubbing, and editing

55Agent

API
#288 · Autoblocks AI

Collaborative evaluation and testing platform to build safe AI apps

55Agent

API

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.

Filter tools

Ranked tools

FAQ