browse_read
Readability MARKDOWN of the current session page (or pass url to navigate first). The READ view.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/browse-read.md
What browse_read does on Gateway
AI agents call browse_read to retrieve information from Gateway without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | — | optional: navigate here first |
browser_id | string | Yes | from browse_open |
Parameters from the server's own tool schema.
Why browse_read is rated Low
This tool retrieves and presents data (page content in markdown format) with no capability to modify, delete, execute commands, or create side effects. It is a straightforward read operation analogous to fetching or viewing content.
From the tool's definition Tool name includes 'browse_read' and description states 'Readability MARKDOWN of the current session page' and 'The READ view' — explicitly focused on retrieving and displaying page content without modification.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
The rule that runs browse_read safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browse_read, this is the rule to start with:
browse_read is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every browse_read call is checked against it from then on.
Questions about browse_read
Readability MARKDOWN of the current session page (or pass url to navigate first). The READ view. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
browse_read accepts 2 parameters: url, browser_id. Required: browser_id. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for browse_read: 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 Gateway. Nothing to install.
browse_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browse_read 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 browse_read. 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.
browse_read is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue