Skip to content
All tool news

Tool desk · Updated daily

Tool news·Vercel·

Exa in the Vercel Agent Marketplace Brings Live Search to AI Apps.

Vercel adds Exa to its Agent Marketplace, giving AI apps native access to fresh web search, one API key, and integrated billing.

CW

Create With tool desk

1 source checked · 3 min read · 3 sections

ShareLinkedIn
Exa in the Vercel Agent Marketplace Brings Live Search to AI Apps

Vercel is making it easier for developers to give AI agents access to current information. Exa, a neural web search provider, is now available as a native integration in the Vercel Agent Marketplace, reducing the setup required to add search and research capabilities to an app.

The integration, announced in Vercel’s changelog, provides a single API key that works across Exa’s products. Billing is handled through the developer’s Vercel account rather than through a separate integration and payment workflow.

That combination matters because an AI model’s built-in knowledge is inherently limited by its training data. Connecting an agent to web search can help it answer questions using newer sources, investigate unfamiliar topics, or gather context before generating a response.

What the Exa integration provides

Exa describes its service as a neural search engine designed to return relevant web results for AI applications. Rather than requiring developers to treat search as an entirely separate service, its Vercel listing packages access as a native marketplace integration.

Vercel says developers can use it to build several types of functionality:

  • Search experiences that retrieve current pages and information
  • Research agents that collect sources before producing an answer or summary
  • Context-aware features that supplement model prompts with external information
  • Data retrieval workflows that need information beyond an application’s own database

The implementation shown in Vercel’s announcement uses the exa-js package. A server route reads an EXA_API_KEY environment variable, creates an Exa client, and sends a query through Exa’s search method. The example selects the instant search type, illustrating how developers could place retrieval inside an application endpoint.

This is still an application-level building block, not a complete research agent. Developers remain responsible for deciding when search should run, how results should be ranked or filtered, which content should enter a model’s context, and how citations should be presented to users. They also need to account for potentially unreliable or adversarial material retrieved from the public web.

Why it matters for smaller teams

For small businesses and independent builders, the immediate benefit is operational simplicity. A team can connect Exa within the same ecosystem used to deploy its application, while Vercel handles the associated billing through its existing account. The single API key across Exa products may also reduce credential management as an application expands beyond a basic search call.

Potential use cases include a customer-support assistant that checks current documentation, a market-monitoring tool that collects recent company information, or an internal research agent that finds source material for a report. No-code and low-code builders would still need a compatible connector or custom API step unless their chosen platform supports the Vercel integration directly.

The launch also fits Vercel’s broader push to become infrastructure for agent development, rather than only a frontend deployment platform. The company has been adding model access and agent tooling across its stack, including Gemini 3.7 Flash through AI Gateway and ACP-compatible harnesses for its AI SDK Harness Layer.

Exa’s arrival fills a different part of that stack. Models provide generation and reasoning, while Exa supplies retrieval from the live web. Bringing both closer to the deployment environment can shorten the path from an agent prototype to a production application, although developers still need to design the retrieval logic and evaluate result quality themselves.

Frequently asked questions

What is Exa in the Vercel Agent Marketplace?

Exa in the Vercel Agent Marketplace is a native integration that lets developers add Exa’s neural web search to applications deployed through Vercel. It is intended for search, research agents, and features that need fresh information from the web.

How does the Vercel integration handle authentication and billing?

The integration provides one API key that works across Exa products. Charges are handled through the developer’s Vercel account, according to the announcement.

How much does the Exa integration cost?

Vercel’s changelog announcement does not specify pricing or required plans. Developers should consult the current marketplace listing and account billing information before deploying a production workload.

Sources

1 checked

How we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.

Worth passing on?

ShareLinkedIn

Go deeper on Vercel

Related reading, watching and going.

Everything on Vercel →

The briefing

19 May 2026

How to Migrate Your App from Lovable to Claude Code in 2025

Step-by-step guide to migrating your Lovable app to Claude Code. Learn how to move from Lovable's managed platform to a stack you own and control.

Read →

The briefing

10 Feb 2026

OpenClaw Review: 2 Weeks With This AI Agent

Honest 2-week review of OpenClaw — an autonomous AI agent powered by Claude. We test setup, safety, autonomy, and real value to see if it's worth using.

Read →
34 min

Podcast

My Daughter Built a Website Business, Claude Design First Look & Going All-In on Cloudflare

James and Kieran discuss practical AI-powered development through real-world examples, including a seven-year-old building a website business with Claude Code voice mode, Anthropic's new Claude Design tool, API security challenges in the AI agent era, and Cloudflare's expanding AI infrastructure offerings. The episode covers hands-on experiences with vibe coding, emerging design tools, and the evolving landscape of AI-assisted development.

Watch now ↗

Podcast

53. Why Your Vibe Code Needs Tests, Ditching SaaS & AI Agents That Work While You Sleep

James and Kieran discuss the practical realities of building AI-powered software, emphasizing the importance of testing in vibe-coded applications, exploring alternatives to traditional SaaS tools, and implementing autonomous AI agents for business operations. The episode covers technical topics like Convex databases, app store bottlenecks from AI-generated submissions, and using OpenClaw as a marketing automation agent.

Watch now ↗
38 min

Podcast

52. Your AI Co-Founder: OpenClaw, Manus & the Zero-Person Business

In this Create With podcast episode, James and Kieran are joined by Matt Roberts from Happy Operators for an in-depth discussion on using autonomous AI agents in production. The conversation covers practical experiences with OpenClaw, security considerations, comparison with emerging tools like Manus, and the broader shift toward AI-assisted development. They also discuss the VibeCoding Olympics results, Bubble's new AI capabilities, and research on Claude.MD file effectiveness.

Watch now ↗

Latest tool news

What else changed this week.

All tool news
VercelDigest

What Vercel Shipped in Late October

Vercel shipped quicker static deployments, four AI Gateway models, more free domain choices and new CLI controls in late October. The changes cover developers testing sites…

Vercel

Vercel Adds Submit_feedback to Its MCP

submitfeedback is a new Vercel MCP tool that lets agents and harnesses send bug reports, friction reports and feature requests directly to the Vercel team. Feedback can include…

The Create With Briefing

Don't watch forty changelogs. Read one email.

Every Tuesday: the tool changes worth knowing, real business use cases, and what's on near you. Free, unsubscribe any time.