AI agents call browser_docs to retrieve information from Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only informational tool that retrieves documentation about other browser tools. It has no side effects, does not execute actions, modify data, or trigger external operations. The primary risk is minimal—documentation access could theoretically inform misuse of other tools, but that risk is inherent to documentation itself and does not elevate this tool beyond 'Read' category.
From the tool's definition Tool name 'browser_docs' and description 'Get detailed documentation, return values, examples, and caveats for any browser tool' indicate a retrieval operation that queries and returns existing documentation without modifying or executing code.
Attacks that exploit this kind of access
Get detailed documentation, return values, examples, and caveats for any browser tool. It is categorised as a Read tool in the Browser MCP Server, which means it retrieves data without modifying state.
Register the Browser MCP server in PolicyLayer and add a rule for browser_docs: 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 Browser. Nothing to install.
browser_docs 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 browser_docs 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_docs. 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_docs is provided by the Browser MCP server (ricardodeazambuja/browser-mcp-server). 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 →