Available
Structured Data Extraction
Open public pages and collect lists, tables, article text, links, or other structured fields.
Arcvenza AI Browser MCP
Web MCP
Connect a real JavaScript browser to your AI client through MCP. Describe the goal in natural language, then let your agent browse, interact, extract data, and return screenshots or reports.
Streamable HTTPReal JavaScript browser1 credit per browser task
TransportStreamable HTTP
RuntimeReal JavaScript browser
NetworkArcvenza proxy regions
Billing1 credit / browser task
AuthenticationBearer MCP key
Browser capabilities
One browser layer for data and web workflows.
Give an MCP-compatible AI client the browser primitives it needs while Arcvenza handles execution, session isolation, proxy selection, quotas, and artifacts.
Available
Interactive Automation
Search, paginate, click, type, scroll, and navigate multi-step public web flows.
Available
Web Testing & Debugging
Check text and elements, exercise forms, and inspect console errors or failed network requests.
Available
Screenshots & Artifacts
Capture visual evidence and return saved task artifacts alongside the agent result.
Available
Regional Web Access
Run eligible tasks through available Arcvenza proxy regions when a regional route is needed.
Available
Human Takeover
Hand control to the user for CAPTCHA, SMS verification, or another step that requires a real person.
Task workflow
From an instruction to a browser result.
The AI client plans and calls the tools; Arcvenza executes the browser session and returns observations and artifacts.
Describe the outcome
Name arcvenza_browser, the public target URL, the goal, and the result format. Ask for confirmation before sensitive actions.
Call MCP tools
Your AI client connects over Streamable HTTP and iteratively selects the browser tools it needs.
Operate the page
The remote browser renders JavaScript, interacts with the page, and uses an eligible proxy route when needed.
Return the result
Receive structured data, screenshots, reports, or a short-lived takeover step when human input is required.
Three-minute setup
Connect the AI client you already use.
Create a personal MCP key, add the remote endpoint and Authorization header, then restart the client and verify the tool list.
Create an MCP key
Create a named key in the Arcvenza console and save the full value when it is shown once.
Copy the client config
Use https://www.arcvenza.com/mcp with a Bearer key. Set a 180-second tool timeout where the client supports it.
Restart and verify
Fully restart the app or extension, open a new conversation, and confirm the arcvenza_browser tools are available.
[mcp_servers.arcvenza_browser]
url = "https://www.arcvenza.com/mcp"
http_headers = { "Authorization" = "Bearer arcvenza_mcp_REPLACE_WITH_YOUR_KEY" }
tool_timeout_sec = 180- After saving
- Fully quit and reopen Codex App, CLI, or the IDE extension, then start a new conversation.
- Verify
- Run codex mcp list or open /mcp and confirm arcvenza_browser and its browser tools appear.
Also works with
Windsurf / Cascade
Configure serverUrl with an Authorization header, then refresh MCP in Cascade.
Cline
Use the streamableHttp server type and keep sensitive browser actions out of autoApprove.
Gemini CLI
Use httpUrl, a Bearer header, a 180000 ms timeout, and keep trust disabled for confirmation.
MCP SDK / Custom Agent
Connect with an MCP SDK over Streamable HTTP; do not treat /mcp as a normal REST JSON endpoint.
Billing & safety
Clear boundaries for every browser task.
Keep credentials private, stay within permitted access, and leave human-only verification to the user.
- Starting one browser task consumes one crawler credit; the tool calls inside that task are not each charged one credit.
- The Arcvenza account must have available crawler credits and Web MCP concurrency before a task can start.
- A task can stop when its time or action limit is reached. End stale tasks and retry with a clearer goal when needed.
- Only public HTTP and HTTPS targets are eligible. localhost, private networks, cloud metadata, and protected addresses are blocked.
- CAPTCHA or SMS verification requires human takeover; the service does not promise automatic bypass.
- Use only pages and accounts you are authorized to access, and require confirmation before logins, form submission, downloads, or other consequential actions.
FAQ
Before you connect.
Is every browser tool call billed once?
No. One browser task consumes one crawler credit. The agent can call multiple browser tools inside that task without each call consuming another credit.
Why do the tools not appear after I save the configuration?
Fully restart the AI client or IDE extension and open a new conversation. Existing sessions often keep a cached tool list. Use the client MCP list command to verify the server.
Can every ChatGPT or Claude surface connect directly?
No. Codex and ChatGPT Desktop's Codex host can use the Codex configuration, and Claude Code can connect. ChatGPT Web does not read local config, while Claude.ai Connectors require OAuth support that is not currently provided for this static-key service.
Will the browser automatically bypass CAPTCHAs?
No. Ask the agent to create a human takeover step when CAPTCHA, SMS verification, or another human-only check appears.
Can a task open localhost or a private network?
No. The service accepts eligible public HTTP and HTTPS targets and blocks localhost, private addresses, cloud metadata, and other protected network resources.
Is every task guaranteed to succeed?
No. Site policies, account state, page changes, network conditions, and human verification can affect the result. Give the agent a clear goal and handle blocked steps explicitly.
Ready to connect