DLBrowser MCP server
✓ VerifiedProvides AI agents with self-healing web access that automatically bypasses bot blocks, captchas, and JavaScript walls using an escalating backend engine.
Also known as DekryptLabs/dlbrowser
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- 115
- Latest version
- 4.0.2
- Last commit
- Jul 22, 2026
- License
- MIT
What is DLBrowser MCP?
DLBrowser provides AI agents with self-healing web access that automatically bypasses bot blocks, captchas, and JavaScript walls using an escalating backend engine.
Summary generated from the project's README
About DLBrowser MCP server
DLBrowser provides AI agents with a self-healing web access layer designed to bypass bot detection, captchas, and JavaScript walls. It functions as acquisition infrastructure that automatically escalates through five different backends—starting with lightweight HTTP requests like curl_cffi and moving up to full browser engines like Playwright or Firecrawl—only when a block is detected. This approach ensures high success rates while keeping costs low by using the cheapest method possible for every request.
Developers can integrate this server into MCP clients such as Claude Code, Cursor, Windsurf, Cline, and Codex using a single command. The system is highly observable, providing per-run telemetry that logs the specific backend used and the credits consumed. It also optimizes token usage by returning clean markdown instead of raw HTML, which can reduce context window consumption by approximately 77%. Users can connect via a hosted gateway using an API key or choose to self-host the entire engine for full data privacy.
What you can do with it
- 1Bypass automated bot detectionAn AI agent can access websites protected by Cloudflare or DataDome by automatically escalating through different backend engines.
- 2Reduce LLM token costsA developer can instruct an agent to fetch web content in markdown format to save on API expenses.
- 3Monitor web data expensesA user can track exactly how much each web request costs by reviewing the per-run telemetry.
Written from the project's README. Every use case is checked against a quote from it.
How to install DLBrowser MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall DLBrowser MCP in Claude Code
$ claude mcp add --env 'DLBROWSER_API_KEY=<YOUR_DLBROWSER_API_KEY>' dlbrowser -- uvx dlbrowserInstall DLBrowser MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"dlbrowser": {
"command": "uvx",
"args": [
"dlbrowser"
],
"env": {
"DLBROWSER_API_KEY": "<YOUR_DLBROWSER_API_KEY>"
}
}
}
}Install DLBrowser MCP in VS Code
.vscode/mcp.json
{
"servers": {
"dlbrowser": {
"type": "stdio",
"command": "uvx",
"args": [
"dlbrowser"
],
"env": {
"DLBROWSER_API_KEY": "<YOUR_DLBROWSER_API_KEY>"
}
}
}
}Install DLBrowser MCP in VS Code CLI
$ code --add-mcp '{"name":"dlbrowser","type":"stdio","command":"uvx","args":["dlbrowser"],"env":{"DLBROWSER_API_KEY":"<YOUR_DLBROWSER_API_KEY>"}}'Install DLBrowser MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"dlbrowser": {
"command": "uvx",
"args": [
"dlbrowser"
],
"env": {
"DLBROWSER_API_KEY": "<YOUR_DLBROWSER_API_KEY>"
}
}
}
}Install DLBrowser MCP in Codex
$ codex mcp add dlbrowser --env 'DLBROWSER_API_KEY=<YOUR_DLBROWSER_API_KEY>' -- uvx dlbrowserInstall DLBrowser MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.dlbrowser] command = "uvx" args = ["dlbrowser"] [mcp_servers.dlbrowser.env] DLBROWSER_API_KEY = "<YOUR_DLBROWSER_API_KEY>"
Install DLBrowser MCP in Gemini CLI
$ gemini mcp add -s user -e 'DLBROWSER_API_KEY=<YOUR_DLBROWSER_API_KEY>' dlbrowser uvx -- dlbrowserInstall DLBrowser MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"dlbrowser": {
"command": "uvx",
"args": [
"dlbrowser"
],
"env": {
"DLBROWSER_API_KEY": "<YOUR_DLBROWSER_API_KEY>"
}
}
}
}Configuration
DLBROWSER_API_KEYSecretAPI key for the hosted gateway. Optional — DLBrowser runs fully local without it.
| Name | Description | |
|---|---|---|
| DLBROWSER_API_KEY | API key for the hosted gateway. Optional — DLBrowser runs fully local without it. | Secret |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachabledekryptlabs/dlbrowser is public and reachablegithub.com/dekryptlabs/dlbrowser ↗Pass
- Package names this repository as its sourcedlbrowser names dekryptlabs/dlbrowser as sourcepypi.org/project/dlbrowser/ ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-07-22github.com/dekryptlabs/dlbrowser ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from dlbrowserPass
- No critical advisory in the package or its dependencies14 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubDLBrowser
Your AI agent is blind to the half of the web that fights back.
Cloudflare, captchas, and JavaScript walls block the tools agents use to browse — silently. DLBrowser is the one that gets through. One line. Self-healing. Metered to the credit.
npx dlbrowser connect --key dlb_xxx
Wires DLBrowser into Claude Code, Cursor, Windsurf, Cline & Codex in one command. Your agent gets 11 web tools that actually reach the page.
The 60-second try
pip install dlbrowser
dlbrowser fetch https://example.com
Every fetch tells you which backend got through and how long it took — because the engine picks the cheapest one that works and only escalates when a site fights back:
{ "success": true, "backend": "curl_cffi", "load_time": 0.03, "blocked": false }
And every run is metered against a plan, in the open — no surprise invoice:
{ "plan": "scout", "remaining_daily": 497, "remaining_monthly": 2497,
"upgrade_url": "https://dekryptlabs.github.io/dlbrowser/pricing.html" }
That's a real response from the live gateway. Start free — 2,500 credits, no card.
Why your agent needs this
You wire web access into an agent. It works in the demo. Then it meets the real web:
- One site loads with a 50ms HTTP request. The next is an empty React shell until JS runs.
- Cloudflare and DataDome quietly serve your headless browser a challenge page.
- Your agent's built-in fetch returns
""— not an error, an empty string — and keeps going. - You have no idea which sites failed, which backend would've worked, or what any of it cost.
DLBrowser is the capability layer that fixes this. Not a scraper. Not a crawler. Acquisition infrastructure for AI agents — reliable, observable, billable.
The engine: start cheap, escalate only when blocked
curl_cffi → tls_client → playwright → nodriver (CDP) → firecrawl
~50ms ~200ms full JS max stealth last resort
HTTP-level, no browser │ browser-level, real Chromium
└── auto-escalates when a block is detected
~70% of real fetches never need a browser. Starting with a 50ms request and climbing the ladder only on a detected block keeps you fast and cheap — while still getting through the sites that stop everything else. Five backends. Firecrawl has two. Crawl4AI has one.
What resets your expectations
| 🔁 Self-healing fallback | Five backends auto-escalate on block. Your agent stops getting an empty string. |
| 💸 Per-run cost telemetry | Every run logs backend, credits, and estimated cost to a queryable ledger. No competitor exposes this. Your CFO can finally answer "what does our web data cost?" |
| 🪙 Token-efficient | Returns clean markdown/extracted content, not raw HTML — ~4× fewer tokens into your agent's context on content pages (measured). Lower API cost, more window, better signal. |
| 🎯 No JS multipliers | 1 credit per page on any backend. Firecrawl & ScrapingBee charge 5–7× for JS rendering. |
| 🔒 Atomic metering | Reservation-based — 0% overshoot, even under concurrency. You're never billed past your quota. |
| 🧠 LLM extraction | Natural language → structured JSON. Runs against a local/free model — no cloud key required. |
| 📦 MIT, self-hostable | Full feature parity self-hosted. Your data never leaves your infra. The hosted gateway just saves you running proxies + captcha infra. |
| 🔌 MCP-native | 11 tools with use-first descriptions, so your agent reaches for DLBrowser over its flaky built-in browser. |
Fewer tokens, cleaner signal
Raw HTML pours tags, scripts, and boilerplate into your agent's context — you pay tokens
for noise, and the model burns attention parsing <div class> soup. DLBrowser returns
clean markdown or extracted content instead.
Real measurement through the live gateway — a Wikipedia article:
| Mode | Tokens (approx) | vs raw HTML |
|---|---|---|
| Raw HTML | ~57,000 | — |
| Markdown | ~13,000 | ~77% fewer |
| Article | ~42,000 | ~27% fewer |
~4× less context per fetch on a content page — lower API cost, more room in the window, and better signal for the model to reason over. Savings vary by page (a sparse link list saves little, and your agent picks the mode) — so measure your own:
import asyncio, tiktoken
from hermes_browser import fetch # pip install dlbrowser
enc = tiktoken.get_encoding("cl100k_base")
raw = asyncio.run(fetch(url, mode="html"))["content"]["html"]
md = asyncio.run(fetch(url, mode="markdown"))["content"]["markdown"]
print(len(enc.encode(raw)), "→", len(enc.encode(md)), "tokens")
One line, every host
npx dlbrowser connect --key dlb_xxx
# detects and configures: claude-code · claude-desktop · cursor · windsurf · cline · codex
Or point any MCP client at the free hosted demo gateway (try it with no local setup — some features are gated on the demo; self-host for the full engine):
claude mcp add dlbrowser --transport http \
--url https://api.dekryptlabs.com \
--header "Authorization: Bearer dlb_xxx"
Your agent immediately has: fetch · scrape · smart_extract · screenshot ·
markdown · crawl · search · serp · status · account · topup.
Can I trust it? (architecture)
Agent / CLI / Extension / MCP client
│
┌────┴─────┐
│ Gateway │ Paywalled — 401 no key · 402 over quota · free: status/account
└────┬─────┘
┌────┴─────┐
│ Router │ Adaptive per-domain scoring: success · latency · cost · freshness
└────┬─────┘
┌────┴─────────────────────────────┐
│ curl_cffi → tls → playwright → │ self-healing cascade
│ nodriver → firecrawl │
└────┬─────────────────────────────┘
┌────┴─────┐
│ Ledger │ per-run backend · credits · cost · trace_id (OpenTelemetry)
└──────────┘
The router learns per-domain — more usage, better routing. Everything above the gateway is MIT and self-hostable. Read the code before you trust it; that's the point of open source.
Can it beat Cloudflare?
On many real sites, with no browser at all. We tested 5 Cloudflare-protected sites from a datacenter IP with no residential proxy (worst case):
| Site | Result | How |
|---|---|---|
| nowsecure.nl (CF challenge test) | ✅ pass | TLS impersonation |
| crunchbase.com | ✅ pass | curl_cffi, 0.3s, no browser |
| nike.com | ✅ pass | curl_cffi, 1.2s, no browser |
| g2.com | ❌ 403 | Cloudflare Enterprise — datacenter IP blocked by reputation |
| zillow.com | ❌ 403 | Enterprise + captcha — needs residential IP |
3/5 passed on HTTP-level TLS impersonation alone. The two failures weren't fingerprint failures — they're IP-reputation blocks that need residential-proxy routing (supported, disabled in this test). No tool beats Cloudflare universally; DLBrowser's answer is layered escalation. Full methodology + "what beating Cloudflare actually means" → marketing/cloudflare.md.
We have not published broad head-to-head benchmarks vs Firecrawl/Crawl4AI yet — those are next, with the methodology published alongside. We don't print numbers we made up. Don't trust our table — run it on your own hardest sites:
pip install "dlbrowser[full]" && python3 -m playwright install chromium
dlbrowser fetch <a-url-that-blocks-your-current-tool> # see the backend that got through
Pricing
| Plan | Price | Credits | Daily cap | Backends | Captcha | Proxy | LLM | Keys |
|---|---|---|---|---|---|---|---|---|
| Scout | Free | 2,500 one-time | 500 | curl_cffi | — | — | — | 1 |
| Analyst | $29/mo | 100,000/mo | 5,000 | + tls_client | — | — | 50k | 3 |
| Operator | $85/mo | 500,000/mo | 25,000 | + playwright | ✓ | — | 200k | 10 |
| Command | $299/mo | 2,000,000/mo | 100,000 | all + nodriver | ✓ | ✓ | 1M | 50 |
| Enterprise | from $999/mo | 10M–100M+/mo | — | all + dedicated | ✓ | ✓ | ∞ | ∞ |
1 credit = 1 page, any backend. Annual 20% off. Self-hosting is free forever. Full pricing → PRICING.md · hosted: dekryptlabs.github.io/dlbrowser/pricing.html
Will my company approve it?
- Multi-tenant — organizations, teams, seats, roles
- API keys — create, revoke, rotate, scope, expire (SHA-256 hashed)
- Audit logs — immutable event ledger: who did what, when, at what cost
- Webhooks — HMAC-SHA256 signed, with a dead-letter queue
- SLA monitoring — scheduled page diffing with noise-tolerant change detection
- Self-hosted — Docker one-liner, full feature parity, data stays in your network
Enterprise plans publish real prices (from $999/mo) — no "call us" black box. sales@dekryptlabs.com
When not to use DLBrowser
- You need pre-built datasets → Bright Data / Apify
- You need a visual scraping IDE → Octoparse
- You need screenshot-as-a-service → Urlbox
DLBrowser is for teams running AI agents that need reliable, observable, cost-controlled web access at scale.
Docs
| Resource | Link |
|---|---|
| Getting Started | GETTING_STARTED.md |
| Integrations (LangChain / LlamaIndex) | INTEGRATION_QUICKSTART.md |
| Self-Hosted Deploy | DEPLOYMENT.md |
| Comparison vs Firecrawl / Crawl4AI | COMPARISON.md |
💜 Sponsor DLBrowser
DLBrowser is MIT and free forever, and we keep a free hosted demo gateway running for everyone. Sponsoring funds new backends, published benchmarks, site-specific scrapers, and keeps the free tier free. If it saves your agents from getting blocked — or saves you tokens — please consider it.
Become a sponsor → · tiers from $10/mo to $1,000/mo. Full perks in SPONSORS.md. $25/mo and up puts your name (or logo, at $100+) in the banner below — seen by everyone who visits the repo, the PyPI page, and the npm page.
Our sponsors
Give your agent the whole web.
npx dlbrowser connect --key dlb_xxx
Built by Dekrypt Labs · MIT License · sales@dekryptlabs.com
mcp-name: io.github.DekryptLabs/dlbrowser
DLBrowser MCP questions
How do I add DLBrowser MCP to Claude Code?
Run claude mcp add --env 'DLBROWSER_API_KEY=<YOUR_DLBROWSER_API_KEY>' dlbrowser -- uvx dlbrowser in your terminal. Add --scope user to make it available in every project.
How do I add DLBrowser MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How does the self-healing mechanism work?
The engine uses five different backends that automatically escalate from simple HTTP requests to full browser rendering when a block is detected.
Does DLBrowser help reduce LLM token usage?
Yes, it returns clean markdown or extracted content instead of raw HTML, which can result in approximately 77% fewer tokens for content pages.
Is there a free tier available?
Yes, the Scout plan provides 2,500 one-time credits for free with no credit card required.