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.

#457 · Demodesk

AI agents that record sales meetings, coach reps and update the CRM

40Agent

API
#458 · Tidio

AI customer service platform built around the Lyro AI support agent

40Agent

API
#459 · ShengShu Technology

Multimodal AI video generation with the Vidu model

40Agent

API
#460 · Einride

Autonomous, electric freight powered by the Saga planning platform

40Agent

API
#461 · Bluejay

Automated quality assurance for AI voice and chat agents

40Agent

API
#462 · Abundant

RL environments and human-in-the-loop for agents

40Agent

API
#463 · Civitai

The largest open community for sharing AI art models, images, and LoRAs

40Agent

API
#464 · Respeecher

Hollywood-grade AI voice cloning used in Star Wars and AAA games

40Agent

API
#465 · Mubert

Royalty-free AI music generation for creators, apps, and brands

40Agent

API
#466 · LOVO

AI voice generator with 500+ voices in 100 languages and the Genny video workspace

40Agent

API
#467 · Watershed

Enterprise sustainability platform for carbon accounting and ESG reporting

40Agent

API
#468 · Torq

Agentic AI platform for the autonomous SOC

40Agent

API
#469 · Landingi

No-code landing page builder for digital marketers

40Agent

API
#470 · Token Metrics

AI-powered crypto investment research and analytics

40Agent

API
#471 · Pictory

Turn scripts, blog posts, and documents into videos automatically

40Agent

API
#472 · Supertone

HYBE-backed AI voice technology for music, film, and games

40Agent

API
#473 · Elai

AI avatar video generation for corporate learning, acquired by Panopto

40Agent

API
#474 · Traceloop

LLM observability and reliability built on the open-source OpenLLMetry standard

40Agent

API
#475 · Not Diamond

Data-driven recommendation and routing layer that sends each prompt to the best AI model

40Agent

API
#476 · Martian

LLM model router that dynamically sends each prompt to the best model for cost and performance

40Agent

API
#477 · Silence Laboratories

Private computing infrastructure using MPC to protect secrets, data and keys

40Agent

API
#478 · Langdock

GDPR-compliant enterprise platform for rolling out AI across the whole workforce

40Agent

API
#479 · Pruna AI

Open-source optimization framework that makes AI models smaller, faster and cheaper

40Agent

API
#480 · Adaptyv Bio

Cloud lab that experimentally validates AI-designed proteins in under three weeks

40Agent

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