browser_creds

Extract browser passwords. Auto-selects client.

SERVERClaude C2 SOURCE0xyg3n/claude-c2

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/0xyg3n-claude-c2/browser-creds.md

WHAT IT DOES

What browser_creds does on Claude C2

AI agents call browser_creds to retrieve information from Claude C2 without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why browser_creds is rated Low

Although this is a Read operation (retrieves data with no side effects), the severity is critical because the blast radius of misuse is enormous: extracted browser passwords grant access to numerous user accounts and sensitive systems.

From the tool's definition Tool is named 'browser_creds' with description 'Extract browser passwords.' The function retrieves stored credentials from browser password managers without modification or deletion.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browser_creds safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Claude C2, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_creds, this is the rule to start with:

browser_creds Allowed

browser_creds is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_creds": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Claude C2, apply this rule, and every browser_creds call is checked against it from then on.

FAQ

Questions about browser_creds

What does the browser_creds tool do? +

Extract browser passwords. Auto-selects client. It is categorised as a Read tool in the Claude C2 MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on browser_creds? +

Register the Claude C2 MCP server in PolicyLayer and add a rule for browser_creds: 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 C2. Nothing to install.

What risk level is browser_creds? +

browser_creds is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit browser_creds? +

Yes. Add a rate_limit block to the browser_creds 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_creds completely? +

Set action: deny in the PolicyLayer policy for browser_creds. 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_creds? +

browser_creds is provided by the Claude C2 MCP server (0xyg3n/claude-c2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Claude C2, and thousands of servers like it.

This server

All 94 Claude C2 tools →

Across the catalogue

browser_extract_text on Percepta MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →