fetch_txt
Fetch a website, return the content as plain text (no HTML)
This record as markdown: /tools/cowork-bench/fetch-txt.md
What fetch_txt does on Cowork Bench
AI agents call fetch_txt to retrieve information from Cowork Bench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why fetch_txt is rated Low
This tool performs a read-only operation that fetches and retrieves website content. It has no capability to modify, delete, or execute code. The only potential risk is if the fetched content could be used maliciously downstream, but the tool itself is purely informational. Severity is low because fetching public web content is a standard, benign operation with minimal blast radius.
From the tool's definition 'Fetch a website, return the content as plain text' — retrieves data from a remote resource with no modification, deletion, or code execution.
Attacks that exploit this kind of access
The rule that runs fetch_txt safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fetch_txt, this is the rule to start with:
fetch_txt is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every fetch_txt call is checked against it from then on.
Questions about fetch_txt
Fetch a website, return the content as plain text (no HTML). It is categorised as a Read tool in the Cowork Bench MCP Server, which means it retrieves data without modifying state.
Register the Cowork Bench 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 Cowork Bench. 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 Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
This server
Across the catalogue