Fetch content from a URL with automatic content type detection
AI agents call fetch to retrieve information from MCP URL Fetcher without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from URLs and processes it for reading purposes only. It has no side effects—it queries and returns web content without modifying, deleting, or executing anything. The sibling tools (fetch-html, fetch-json, etc.) reinforce that this is purely a data retrieval mechanism.
From the tool's definition Tool name 'fetch' and description states it 'Fetch[es] content from a URL' with 'automatic content type detection'. The server enables LLMs to 'fetch and process web content' in multiple formats (HTML, JSON, Markdown, text).
Attacks that exploit this kind of access
Fetch content from a URL with automatic content type detection. It is categorised as a Read tool in the MCP URL Fetcher MCP Server, which means it retrieves data without modifying state.
Register the MCP URL Fetcher MCP server in PolicyLayer and add a rule for fetch: 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 MCP URL Fetcher. Nothing to install.
fetch 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 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. 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 is provided by the MCP URL Fetcher MCP server (nathanonn/mcp-url-fetcher). 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 →