read_web_documentation
AI agents call read_web_documentation to retrieve information from Amazon Q Web Documentation Reader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and extracts documentation content from websites with no side effects. It performs information retrieval only, matching the 'Read' category definition of queries that retrieve data without modifications or destructive actions.
From the tool's definition Tool name is 'read_web_documentation' and server description states it 'extract[s] clean content, and retrieve[s] code examples from web documentation.' The sibling tools include 'extract_code_examples', 'get_documentation_links', 'get_page_structure', and…
Attacks that exploit this kind of access
read_web_documentation. It is categorised as a Read tool in the Amazon Q Web Documentation Reader MCP Server, which means it retrieves data without modifying state.
Register the Amazon Q Web Documentation Reader MCP server in PolicyLayer and add a rule for read_web_documentation: 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 Amazon Q Web Documentation Reader. Nothing to install.
read_web_documentation 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 read_web_documentation 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 read_web_documentation. 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.
read_web_documentation is provided by the Amazon Q Web Documentation Reader MCP server (lumos-labs-hq/amazon-q-docmcp). 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 →