read_documentation
AI agents call read_documentation to retrieve information from AWS Documentation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reads AWS documentation content with no side effects, modifications, or external operations. It aligns with the 'Read' category as it queries documentation resources and returns information. The low severity reflects that reading documentation poses minimal risk—it cannot delete, modify, execute code, or affect resources.
From the tool's definition Tool named 'read_documentation' with server description stating it 'fetches and converting documentation pages to markdown, searching AWS docs, and getting content recommendations'.
Attacks that exploit this kind of access
read_documentation. It is categorised as a Read tool in the AWS Documentation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS Documentation MCP Server MCP server in PolicyLayer and add a rule for read_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 AWS Documentation MCP Server. Nothing to install.
read_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_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_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_documentation is provided by the AWS Documentation MCP Server MCP server (joseph19820124/aws-doc-sse). 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 →