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.
Filter tools
Filters
Showing 24 of 2662 tools.
Ranked tools
- 10Agent#2473 · Insider One
The leading Agentic Customer Engagement Platform for continuous AI decisioning and autonomous end-to-end engagement.
- 10Agent#2474 · Domyn
The agentic AI platform for regulated enterprises, offering full control over models, data, and infrastructure.
- 10Agent#2475 · Sixfold
Sixfold is the AI brain that handles the heavy lifting in insurance submissions, empowering underwriters to build more profitable portfolios.
- 10Agent#2476 · Machina Labs
Intelligent, agile, software-defined manufacturing that turns design intent into precise metal structures in days.
- 10Agent#2477 · Maven AGI
Enterprise AI agent platform for customer experience that delivers exceptional service at every touchpoint.
-
- 10Agent#2479 · Reach Security
Proactively identify and remediate security control misconfigurations to close gaps faster than AI-powered attacks.
- 10Agent#2480 · Prophet Security
Empower your SOC with a fleet of autonomous AI agents that accelerates Tier 1, Tier 2, and Tier 3 tasks.
- 10Agent#2481 · Sardine
The top agentic risk platform for real-time fraud prevention, AML compliance, and AI-driven attack protection.
- 10Agent#2482 · Credo AI
One platform to discover, assess, and govern every AI agent, model, and application — continuously and in context.
- 10Agent#2483 · Replo
Go from product to store to sale—all with one AI-powered solution for e-commerce.
-
- 10Agent#2485 · Wysa
Wysa offers anonymous, evidence-based AI mental health support for individuals, teams, and health systems.
- 10Agent#2486 · Polycam
AI reality capture for professionals across any device, for any user, and any project.
- 10Agent#2487 · Tripo
Generate production-ready 3D models from text, images, or sketches in seconds with AI-powered tools.
- 10Agent#2488 · Fliki
Transform text into stunning videos with lifelike AI voices and dynamic AI video clips.
- 10Agent#2489 · Equals
Equals is the first new spreadsheet in 20 years, engineered for AI and designed for trust.
- 10Agent#2490 · Karat
The world's leader in technical interviewing, transforming organizations for the Human + AI era.
- 10Agent#2491 · Brisk Teaching
AI education platform helping teachers create materials, give feedback, and adapt instruction within Google and Microsoft tools.
- 10Agent#2492 · Octane AI
The #1 AI-powered product quiz platform for Shopify that turns browsers into buyers.
- 10Agent#2493 · Nosto
AI-powered ecommerce personalization, search, and merchandising solutions to drive sales and foster loyalty.
- 10Agent#2494 · H2O.ai
The convergence of the world's best predictive and generative AI for private, protected data.
- 10Agent#2495 · Dataiku
The platform for AI success, powered by people, orchestration, and governance, built for enterprise scale.
-
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.