web_login
Opens a real browser window on the Mac for the user to sign into a website themselves (you never handle their password). After they log in, the session is saved on this Mac and reused by web_navigate/web_read/web_screenshot — they won't need to log in again. Use a stable session name per site (e....
This record as markdown: /tools/com-local-mcp-local-mcp/web-login.md
What web_login does on Local
AI agents invoke web_login to trigger actions in Local. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | Yes | The site's login URL to open, e.g. https://www.linkedin.com/login |
session | string | — | A stable name for this login profile, e.g. 'linkedin'. |
Parameters from the server's own tool schema.
Why web_login is rated High
This tool triggers an external browser operation (opening a real browser window) and persists session state on the machine. It executes a browser action with lasting side effects (saved session credentials), making it Execute rather than Read or Write.
From the tool's definition Opens a real browser window on the Mac for the user to sign into a website themselves... the session is saved on this Mac and reused by web_navigate/web_read/web_screenshot
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs web_login safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For web_login, this is the rule to start with:
web_login 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every web_login call is checked against it from then on.
Questions about web_login
Opens a real browser window on the Mac for the user to sign into a website themselves (you never handle their password). After they log in, the session is saved on this Mac and reused by web_navigate/web_read/web_screenshot — they won't need to log in again. Use a stable session name per site (e.g. 'linkedin'). NOTE: automating sites like Instagram/LinkedIn may violate their terms — the user accepts that risk. It is categorised as a Execute tool in the Local MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
web_login accepts 2 parameters: url, session. Required: url. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for web_login: 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 Local. Nothing to install.
web_login is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the web_login 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 web_login. 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.
web_login is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
Across the catalogue