Store a credential for later use with browser_type_credential. The credential is saved to the local credentials file (~/.mcproxy/credentials.json). WARNING: Only use this for initial setup - prefer setting credentials via environment variables for production use.
AI agents use browser_set_credential to create or update resources in MCProxy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCProxy environment.
This tool creates or modifies persistent credential data in a local file. While not destructive (data can be overwritten), it writes sensitive authentication material to disk, making it a Write action with high severity due to the security implications of storing credentials—especially in a headless browser automation context where misuse could compromise accounts across geographically distributed systems.
From the tool's definition 'Store a credential for later use' and 'saved to the local credentials file (~/.mcproxy/credentials.json)' indicate persistent data creation/modification; WARNING about production use suggests elevated risk exposure.
Attacks that exploit this kind of access
Store a credential for later use with browser_type_credential. The credential is saved to the local credentials file (~/.mcproxy/credentials.json). WARNING: Only use this for initial setup - prefer setting credentials via environment variables for production use. It is categorised as a Write tool in the MCProxy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCProxy MCP server in PolicyLayer and add a rule for browser_set_credential: 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 MCProxy. Nothing to install.
browser_set_credential is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the browser_set_credential 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.
Set action: deny in the PolicyLayer policy for browser_set_credential. 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.
browser_set_credential is provided by the MCProxy MCP server (saladtechnologies/mcproxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →