Pricing

Free.

No credits, no quotas, no per-lookup charges, on either plan. The only limits are rates, to keep bulk scrapers out, and they are printed below rather than hidden. Pro is for the few who run into them.

Free
$0, forever
Get a free API key
Pro
$99 a year, annual only
Search and company pagesUnlimitedUnlimited
Tech stacks and web signalsUnlimitedUnlimited
REST API and MCP server, every endpointUnlimited, no monthly capUnlimited, no monthly cap
Contact reveals (emails, people)1,000 a day, resets nightly10,000 a day, resets nightly
Request rate5,000 per 5 h, 5 a second25,000 per 5 h, 20 a second
Companies touched5,000 a day25,000 a day
Priority crawl of your own list–✓
Bulk export–✓
Commercial licence–✓
Email support–✓
Works with
ClaudeChatGPTCodexGeminiCursorWindsurfVS CodeGitHub CopilotZedClineRaycastClayn8nZapierMakeHubSpotGoogle SheetsAirtableSalesforceNotionSlackLangChain
Any MCP client, and anything that can make an HTTP request.
Our takeThis is the plan. Nothing is metered; the rates exist so one script cannot copy the database, and almost nobody meets them. No card, no trial, no credits.Only if you hit the free caps. Annual, cancel any time, and the free plan is still there if you do.

One bucket per account across the website, the API and the MCP server. Contact reveals reset at midnight UTC; a company you have already revealed stays open for 30 days without using another. Full detail in the docs; what the data covers on the live data page.

Fair use: the site and the API share one set of limits per account (per IP without one): 5,000 requests every 5 hours and 5,000 distinct companies a day on a free key, 25,000 and 25,000 on Pro; without a key 300 requests and 200 companies. Up to 50 domains a day can be pushed to the front of the crawl (500 on Pro); more still queue, at normal priority. New free accounts start at 100 reveals a day for their first week when several are created from one address. Accounts used to copy the database in bulk are closed.

Why it is free

Hi, we're Duda and Nick. Founders that build things together.

One of those things is AgentData. It crawls the web 24 hours a day, profiling every company it finds: what tech they use, who works there, how to reach them.

So far it has indexed 128.3 million companies, found 7.8 million email addresses, and detected 3,625 technologies. The number goes up every day, and the live data page shows exactly how much of it is verified.

We thought this data was too useful to sit behind a paywall. So we made it free. All of it. The search, the company profiles, the emails, the API, the MCP server, everything. Just sign up.

Our business is built on our commercial products: Drag, HeyHelp, and Oneway. Drag is AI-powered team collaboration, HeyHelp is an AI email assistant, and Oneway is an all-in-one customer platform. If you're managing a team or doing outreach, we think you'll love them. But AgentData is genuinely free whether you try them or not.

If you have ideas for how to make it better, we'd love to hear from you at support@agentdata.run

Thanks for being here.

Duda & Nick

What pays for it

AgentData is subject to fair use limits to prevent abuse. See our terms for details. Questions? support@agentdata.run