Byob

33 tools. 21 can modify or destroy data without limits.

21 write tools that can modify data. Rate limits recommended.

Last updated:

21 can modify or destroy data
12 read-only
33 tools total

Community server · catalogue entry verified 27/06/2026

How to control Byob ↓

What Byob exposes to your agents

Read (12) Write / Execute (21) Destructive / Financial (0)
High Risk

The most dangerous Byob tools

21 of Byob's 33 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Byob

PolicyLayer is an MCP gateway — it sits between your AI agents and Byob, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations
{
  "browser_close_tab": {
    "limits": [
      {
        "counter": "browser_close_tab_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "browser_start_record_network": {
    "limits": [
      {
        "counter": "browser_start_record_network_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Byob — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON BYOB →

Instant setup, no code required.

All 33 Byob tools

EXECUTE 18 tools
Execute browser_emulate_device Emulate a device viewport. Use Execute browser_eval Run arbitrary JavaScript in a browser tab via CDP Runtime.evaluate. Execute browser_hover Move the mouse over the element matching the given CSS selector to trigger Execute browser_intercept_start Start a request-interception session in a tab. Provide an array of Execute browser_intercept_stop Stop a Execute browser_navigate Open a new tab (or reuse a given tabId) and navigate to the URL. Execute browser_stop_record_network Stop a recording previously started with browser_start_record_network and Execute browser_wait_for Block until a CSS selector reaches the requested state (visible / hidden / attached / detached). Execute browser_go_back Go back one step in the browser history of the given tab and wait for the new page Execute browser_go_forward Go forward one step in the browser history of the given tab and wait for the new Execute browser_click Click an element matching the given CSS selector in the active browser tab. Execute browser_drag Drag the mouse from Execute browser_press_key Send a single keyboard event to the page (e.g. Enter, Escape, Tab, F5, ArrowDown, Execute browser_scroll Scroll the page to a position, an element, or absolute Y coordinate. Execute browser_select Choose an <option> in a native <select> by exactly one of value, label, or index. Execute browser_switch_tab Bring the given tab to the foreground (focus its window + make it active). Execute browser_type Focus the element matching the selector, then type the given text. Execute browser_upload_file Upload one or more local files to a

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Byob

How do I prevent bulk modifications through Byob? +

The Byob server has 3 write tools including browser_close_tab, browser_print_pdf, browser_set_cookies. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Byob.

How many tools does the Byob MCP server expose? +

33 tools across 3 categories: Execute, Read, Write. 12 are read-only. 21 can modify, create, or delete data.

How do I enforce a policy on Byob? +

Register the Byob MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Byob tool call.

Deterministic rules across all 33 Byob tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

33 Byob tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.