browser

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/alexgladkov-claude-in-mobile/browser.md

WHAT IT DOES

What browser does on Claude Mobile

AI agents invoke browser to trigger actions in Claude Mobile. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why browser is rated High

The 'evaluate: run JS' capability demonstrates this tool can execute arbitrary code in the browser context, which classifies it as Execute rather than Write. While it also performs Read operations (screenshots) and Write operations (filling forms), the ability to execute JavaScript code represents the most severe capability.

From the tool's definition Tool enables browser automation with capabilities to 'navigate/click/fill/fill_form/press_key: interaction' and crucially 'evaluate: run JS' which allows execution of arbitrary JavaScript code.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browser safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Mobile, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser, this is the rule to start with:

browser Rate-limited

browser stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser": {
      "limits": [
        {
          "counter": "browser_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every browser call is checked against it from then on.

FAQ

Questions about browser

What does the browser tool do? +

Browser automation. open/close/list_sessions: session management. navigate/click/fill/fill_form/press_key: interaction. snapshot/screenshot: capture. evaluate: run JS. wait_for_selector: wait for element. It is categorised as a Execute tool in the Claude Mobile MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for browser: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Mobile. Nothing to install.

What risk level is browser? +

browser is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit browser? +

Yes. Add a rate_limit block to the browser rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block browser completely? +

Set action: deny in the PolicyLayer policy for browser. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides browser? +

browser is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Claude Mobile, and thousands of servers like it.

This server

All 198 Claude Mobile tools → High-risk tools on this server →

Across the catalogue

browser_click on Percepta MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →