AgentBrowse · web access for AI agents

Let your AI read the public web — safely, with proof

Your agent asks a question about a webpage. We return a clear answer with short quotes, the page title, and the URL so you can check what it saw. You get free reads every day. Want more privacy? Run a small Companion app on your computer so pages open from your internet, not ours. Same login and API key as the rest of Agent Media Tools.

Free daily reads Quotes you can check Safe by default Optional private mode One shared credit balance
Try it free → Why this is better Verification How it works Download Companion Private mode Pricing For developers

Verified on live sites — not just a demo

Public catalog suite (server HTTP reader): 28/28 hard requirements on the latest run, including 2/2 private-network blocks that must never succeed. Soft outcomes (JS walls, timeouts) return clear codes — we don’t invent page content.

Full snapshot, limits, and “what we don’t claim”: AgentBrowse verification →

Why this beats the web access agents already have

Your agent can already “use the internet” in a few common ways. Here’s why people switch to AgentBrowse when they care about trust, safety, and cost.

Bottom line: same goal (agent reads a page) — with proof, guardrails, free daily use, and private mode when you want it. One API key with the rest of Agent Media Tools. See live verification numbers.

demo · example.com
Illustrative · sites verified by our reader suite

How it works

  1. Your agent asks about a public page — for example “What does this pricing page say?”
  2. Who opens the page?
    • With Companion — the page opens from your computer and home/office internet (more private).
    • Without Companion — we open the public page on our side when we have room.
  3. You get proof back — short quotes, title, and URL so you can verify what was seen.
  4. Safety first — each task lists which sites it may touch. Private/home networks and cloud admin addresses are blocked so agents can’t wander where they shouldn’t.

Private when you want it

Install the optional Companion app. Pages load on your device. We only assign the job and return the result — we don’t need to pretend to be your browser on our servers.

Safe for agents

We block private networks and sensitive cloud addresses. You choose which websites each task is allowed to visit.

Proof you can check

Answers include short quotes, the page title, and the URL — so you’re not trusting a black box.

Works without installing anything

No Companion? Public pages still work when our servers have capacity. Harder sites (or busy servers) may ask you to turn Companion on.

Download Companion 0.3.0 beta

Private by design: pages open from your home or office internet — not a shared cloud worker. One file per OS, no Node install.

Linux x64 ↓ Windows x64 ↓ macOS Apple Silicon ↓ macOS Intel ↓ SHA256

Binaries: release details · Verify the published SHA-256 checksum before running · From source: npm run companion:tray · Beta builds are not code-signed or notarized yet (Gatekeeper/SmartScreen may prompt).

When a page needs more than HTTP

Our default server path is a light public-page reader. Client-heavy apps behave differently:

Mode auto tries Companion first when online, then server HTTP, then asks for Companion again on JS walls — you rarely need to pick a mode manually.

Why Companion privacy matters

With Companion connected, fetch runs on your device and your ISP path. Sites see a normal residential or office connection — not a shared cloud worker IP. We only assign the job and return structured results.

Docs: AgentBrowse docs. Optional future: Chrome extension for already-logged-in sessions.

Free to start. Clear after that.

No surprise product plan. Everyday page reads include a free daily allowance. After that, successful reads use one flexible credit — the same pool as screenshots and other light tools.

Why charge after free? Free covers exploration. After that, a small credit pays for login checks, keeping track of each job, saving results, and reading pages on our servers when we have room. If our servers are busy — or you use Companion — the heavy lifting moves to your computer. Shared capacity is limited; light metering keeps free use fair for everyone. Full details: Pricing.

For developers

Recommended default: mode: "auto" — Companion if online, else capacity-gated server HTTP; on JS walls / bot blocks, falls back to Companion (or waits until you connect). REST POST /api/browser/browse and MCP browse_web share the same body fields and response shape.

ModeWhat it doesUsage
auto ★Default. Companion → HTTP → Companion on JS/bot wallsAs used
http_readServer public HTML only (no Companion rewrite unless local-first + device online)Free daily → 1 credit
local_browserAlways Companion; parks as waiting_for_local_browser if offlineCompanion required
cloud_browserServer Chromium (operator opt-in only)3 credits when enabled

evidence: "short" (default) or "paragraph" for longer research quotes. Companion status: GET /api/browser/companion.

MethodPath
POST/api/browser/browseSync browse
POST/api/browser/tasksAsync task
GET/api/browser/tasks/:idPoll result
MCPbrowse_webSame payload

Safety: SSRF blocks for private IPs and cloud metadata; allowed_domains required. Capacity: server HTTP sheds under RAM/load/slot pressure (GET /v1/policy on the runtime). Local bridge: WS /bridge/ws.

API landing llms.txt OpenAPI Agent Hub Docs

Example request

After free daily reads, a successful page read uses one flexible credit.

curl -X POST https://agentmediatools.com/api/browser/browse \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "goal": "What is this page about?",
    "start_url": "https://example.com",
    "allowed_domains": ["example.com"],
    "mode": "auto"
  }'

Common questions

Do I need a separate product key?

No. Use your normal Agent Media Tools API key. Usage shares the same flexible credit balance as other tools.

What does this actually do?

It lets an AI agent read public webpages and return answers with short quotes and links you can verify. Optional Companion app = pages open from your computer instead of ours.

Is my browsing private?

With Companion connected: yes for page downloads — they use your internet. We only coordinate the job and return structured results. Without Companion: public pages are read through our service (with safety limits). We don’t open private/home networks either way.

Why not use the web access my agent already has?

Built-in model browse is fine for casual chat, but weak on proof and control. DIY fetch/Playwright means you run the infra and the safety risk. AgentBrowse gives allowlisted public reads, blocked private networks, quotes you can verify, free daily usage, and optional Companion private mode — under the same key as your other tools. See Why this is better.

How is this different from structured-scrape?

Structured scrape fills a fixed list of fields (like “price”, “title”). AgentBrowse is better when you want research-style answers with proof quotes, not a rigid form.

What if a site blocks bots?

You’ll get a clear message. Turning on Companion often helps (real user network). If we charged you and our service was down, that usage is refunded.

Can it open my Gmail?

Not through our servers. That needs Companion plus the Chrome extension so actions stay in your logged-in browser session.

What’s all the developer jargon?

Modes like auto / http_read / local_browser, SSRF protection, MCP browse_web, and capacity gates are for builders — see For developers. Everyday use only needs an API key and (optionally) Companion.

Give your agent the public web

Start on the free daily allowance. Add Companion when you want pages to open from your computer.

Create free account → API landing Docs

Related: Structured scrape for fixed field extraction · Pricing · Agent Hub for keys and MCP.