New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

test_auth_flow

A other tool on the Looking Glass MCP server.

SERVERLooking Glass SOURCElooking-glass-mcp
Low RISK CLASS
Category Other
Parameters 86 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-sahib-sawhney-wh-looking-glass-mcp/test-auth-flow.md

What test_auth_flow does on Looking Glass

AI agents call test_auth_flow as a supporting operation in Looking Glass workflows.

ParameterTypeRequiredDescription
url string Yes Login page URL
waitForUrl string Wait for URL to match after login
passwordValue string Yes Password
usernameValue string Yes Username or email
submitSelector string Yes CSS selector for submit/login button
waitForSelector string Wait for this element after login
passwordSelector string Yes CSS selector for password input
usernameSelector string Yes CSS selector for username/email input

Parameters from the server's own tool schema.

Why test_auth_flow is rated Low

The description is empty, so the exact behavior cannot be determined. The name suggests testing an authentication flow, which could involve reading, writing, or executing actions. Given the context of an AI-native browser server with vault capabilities, this could interact with credentials.

From the tool's definition Tool name is 'test_auth_flow'; description is empty or uninformative.

Risk signalsAccepts URL/endpoint input (url)

Questions about test_auth_flow

What does the test_auth_flow tool do? +

test_auth_flow is a other tool on the Looking Glass MCP server. It is categorised as a Other tool in the Looking Glass MCP Server, which means it performs auxiliary operations.

What parameters does test_auth_flow accept? +

test_auth_flow accepts 8 parameters: url, waitForUrl, passwordValue, usernameValue, submitSelector, waitForSelector, passwordSelector, usernameSelector. Required: url, passwordValue, usernameValue, submitSelector, passwordSelector, usernameSelector. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on test_auth_flow? +

Register the Looking Glass MCP server in PolicyLayer and add a rule for test_auth_flow: 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 Looking Glass. Nothing to install.

What risk level is test_auth_flow? +

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

Can I rate-limit test_auth_flow? +

Yes. Add a rate_limit block to the test_auth_flow 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 test_auth_flow completely? +

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

test_auth_flow is provided by the Looking Glass MCP server (looking-glass-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Looking Glass, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Looking Glass's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.