get_docs
AI agents call get_docs to retrieve information from CSS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the server's stated capability of 'MDN documentation retrieval' and the tool name 'get_docs', this appears to be a read-only operation that queries and returns documentation. It has no side effects, does not execute code, and does not modify data. The empty tool description reduces confidence slightly, but the naming convention and server context clearly indicate a retrieval operation.
From the tool's definition Tool name 'get_docs' and server description indicating 'MDN documentation retrieval' suggest this tool retrieves documentation without modifying data. No description provided for the specific tool, lowering confidence.
Attacks that exploit this kind of access
get_docs. It is categorised as a Read tool in the CSS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CSS MCP Server MCP server in PolicyLayer and add a rule for get_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 CSS MCP Server. Nothing to install.
get_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 get_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 get_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.
get_docs is provided by the CSS MCP Server MCP server (lesleslie/css-mcp). 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 →