AI agents call get_content to retrieve information from Wraith without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries the current state of a web page without modifying it, executing code, or triggering side effects. It is purely informational, similar to fetching or reading content. While the server as a whole enables browser automation (including potential misuse), this specific tool only extracts and returns existing page content.
From the tool's definition The tool 'get_content' returns the current page as clean markdown with no LLM or screenshot processing. The verb 'return' and description 'clean markdown' indicate data retrieval only.
Attacks that exploit this kind of access
Return the current page as clean markdown (no LLM, no screenshot). It is categorised as a Read tool in the Wraith MCP Server, which means it retrieves data without modifying state.
Register the Wraith MCP server in PolicyLayer and add a rule for get_content: 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 Wraith. Nothing to install.
get_content 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_content 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_content. 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_content is provided by the Wraith MCP server (koreahwan/wraith-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 →