Browsa
Trình duyệt đám mây cho tác nhân AI: thực hiện mọi tác vụ web bằng tiếng Anh thông thường trên Phantom, trình duyệt riêng của Browsa, với liên kết xem trực tiếp, lịch chạy, webhook có chữ ký và thông tin đăng nhập đã lưu.
Tài liệu
@browsa/mcp
Drive real browsers from Claude Desktop, Cursor, Cline, and any MCP-compatible client.
MCP (Model Context Protocol) server for Browsa: turn any LLM into a real-browser agent with one config line. The agent gets a fresh cloud Chromium on Browsa's own build, and a live view link so you can watch it work.
What this is
Most "AI agent" setups stop at the LLM. We give the LLM a real browser. Through MCP, Claude can now:
- Navigate, fill forms, click, scroll, scrape
- Return results as structured JSON
- Use your own HTTP or SOCKS5 proxy per browser, or a tier of Browsa's built-in network where it is on (see
proxy_network) - Stay logged in across calls via persistent identities
No code from you: just configure Claude Desktop (or Cursor / Cline / Zed) once, and ask in natural language.
Install
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"browsa": {
"command": "npx",
"args": ["-y", "@browsa/mcp"],
"env": {
"BROWSA_API_KEY": "agt_live_..."
}
}
}
}
No LLM secret goes in the config: save your Anthropic, OpenAI or Google key once at app.browsa.io/dashboard/llm-keys and tasks use the workspace's default saved key. (Prefer to keep it local? Add "BROWSA_LLM_API_KEY": "sk-ant-..." instead.)
Restart Claude Desktop. Ask: "Go to news.ycombinator.com and tell me the top story title."
Cursor
~/.cursor/mcp.json:
{
"mcpServers": {
"browsa": {
"command": "npx",
"args": ["-y", "@browsa/mcp"],
"env": { "BROWSA_API_KEY": "agt_live_..." }
}
}
}
Cline / Continue / Zed
Any MCP-spec-compliant client. Point at npx -y @browsa/mcp and set BROWSA_API_KEY.
Env
| Var | Required | What |
|---|---|---|
BROWSA_API_KEY | yes | Your agt_live_* key from browsa.io → Keys |
BROWSA_LLM_KEY_ID | no | Id of a saved LLM key to use by default (see list_llm_keys). Without it, the workspace's default saved key for the model's provider is used |
BROWSA_LLM_API_KEY | no | A per-task LLM provider key sent with every task. Not needed once a key is saved at dashboard/llm-keys. Wins over BROWSA_LLM_KEY_ID |
BROWSA_LLM | no | Default LLM, e.g. anthropic:claude-sonnet-5-5, or a hosted tier such as browsa-fast. Unset: the saved key's provider default model (claude-opus-5-5 with BROWSA_LLM_API_KEY) |
BROWSA_COUNTRY | no | Default egress country (e.g. US) |
BROWSA_BASE_URL | no | Override prod URL (staging / self-hosted) |
Which LLM key a task uses
Per call, first match wins: a hosted tier (llm: "browsa", "browsa-fast" or "browsa-smart": no key, see Models), then llm_api_key, then llm_key_id, then BROWSA_LLM_API_KEY, then BROWSA_LLM_KEY_ID. With none of these, no key is sent and the server uses the workspace's default saved key for the provider of llm (with llm unset: the first default in the order anthropic, openai, google).
If no key is saved at all:
- No model named (no
llmargument, noBROWSA_LLM):run_taskandcreate_schedulestill work with zero config. They retry once on Browsa's hosted model (which adds credits per task) and the result has anotesaying so: "No saved LLM key found, so this ran on Browsa's hosted model (adds credits per task; see list_models). Save a key at https://app.browsa.io/dashboard/llm-keys to use your own." The same happens if the server has saved keys turned off (LLM_KEYS_UNAVAILABLE). A schedule created this way stays on the hosted model; create it again after saving a key. - A model named: there is no fallback. The tool returns an error (code
LLM_KEY_REQUIRED) that says to save a key at app.browsa.io/dashboard/llm-keys, setBROWSA_LLM_API_KEY, or passllm: "browsa".
Models
run_task and create_schedule take llm and reasoning:
llm | What it is |
|---|---|
"browsa" | The default hosted model |
"browsa-fast" | Fastest and lightest |
"browsa-smart" | For harder tasks |
anything else, e.g. "anthropic:claude-sonnet-5-5" | A provider model, run with your own key (saved, or llm_api_key) |
Hosted tiers need no LLM key and add a flat number of credits per task. Which model each tier runs on, and what it costs, are server settings that can change: the list_models tool returns them (free, read-only), along with the providers you can bring a key for.
reasoning is "low", "medium" or "high"; leave it out for the tier's or the provider's default. Ask in plain language, for example: "Use browsa-smart with high reasoning to compare the pricing pages of these three sites."
run_task and get_job results carry status and outcome. status: completed only means the run ended; outcome: failed with it means the agent finished but could not do the task, and outcome_message and final_result say why. signals lists what was seen on the way (a bot check, a proxy failure) when there is any.
When the job has them, run_task and get_job results include usage (input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, requests), llm_tier, reasoning (the level that was applied) and llm_cost_usd. llm_cost_usd is an estimate from public list prices for runs with your own key; it is null when unknown and always null for hosted runs, which are paid in credits.
Tools exposed
| Tool | What |
|---|---|
run_task | Run a browser-driven task. Returns the final result, outcome and steps. Optional llm, reasoning, llm_key_id. |
get_job | Poll a long-running task. Optional server-side wait_seconds. |
cancel_job | Cancel a running task. |
respond_to_job | Answer an input_required prompt (a decision, or a CAPTCHA the task could not solve itself: see https://browsa.io/captcha). |
start_browser | Start a real cloud browser and get its CDP URL, to drive yourself with Playwright or Puppeteer. |
stop_browser | Stop a browser from start_browser and release it. |
proxy_network | Whether Browsa's built-in proxy network is on, its tiers, countries and price. Read-only and free. |
observe | Read the page of a browser from start_browser as compact text with element ids. No Playwright needed. |
act | One action in that browser (click, type, press, select, scroll, navigate, wait and more); returns what changed. |
list_browsers | List this workspace's browsers and their status. |
credits | Show credit balance + top-up packs. |
list_webhooks / create_webhook / delete_webhook | Webhook CRUD. |
list_identities | List persistent browser identities (use one via profile_id to reuse warmed cookies). |
create_schedule / list_schedules | Recurring tasks. create_schedule takes llm, reasoning and llm_key_id; the schedule stores only the key's id. |
list_job_files | Output files a task wrote. |
list_llm_keys | Saved LLM keys: id, provider, masked key, default flag, status. Read-only; never returns a secret. |
list_models | Hosted tiers (model, default reasoning, credits per task) and own-key providers. Read-only and free. |
Why MCP-first matters
Most agent platforms gate distribution behind "write code → deploy → call our API." We gate it behind "paste config → ask Claude." For an AI agent platform, the prospect's first 30 seconds is the make-or-break moment. With this MCP server, the first 30 seconds is a working browser doing what they asked.
Source + Issues
- Docs: https://browsa.io/docs
- Support: mailto:support@browsa.io
- API reference: https://browsa.io/docs
License
MIT.
