Fetch a website, return the content as plain text (no HTML)
AI agents call fetch_txt to retrieve information from Fetch 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 web content and returns it in a specific format. It has no side effects on the target system—it does not execute code, modify data, delete content, or trigger external operations. The blast radius is minimal; misuse would amount to unauthorized information gathering, which is a Read-category risk.
From the tool's definition Tool name 'fetch_txt' and description 'Fetch a website, return the content as plain text' indicate data retrieval with no modification or deletion. The verb 'fetch' and the explicit output format (plain text) confirm read-only semantics.
Attacks that exploit this kind of access
Fetch a website, return the content as plain text (no HTML). It is categorised as a Read tool in the Fetch MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Fetch MCP Server MCP server in PolicyLayer and add a rule for fetch_txt: 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 Fetch MCP Server. Nothing to install.
fetch_txt 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 fetch_txt 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 fetch_txt. 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.
fetch_txt is provided by the Fetch MCP Server MCP server (tokenizin/mcp-npx-fetch). 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 →