Fetch a URL with HTTP request options
AI agents call search.fetch to retrieve information from MCP Fullstack 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 a URL via HTTP GET/POST requests. While it can make various types of HTTP requests, the core function is to fetch and return content—a read operation. It has no inherent side effects (no data creation, modification, deletion, or financial impact).
From the tool's definition Tool name is 'search.fetch' with description 'Fetch a URL with HTTP request options'. The verb 'fetch' combined with 'URL' and 'HTTP request' indicates retrieval of remote content without modification.
Attacks that exploit this kind of access
Fetch a URL with HTTP request options. It is categorised as a Read tool in the MCP Fullstack MCP Server, which means it retrieves data without modifying state.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for search.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 Fullstack. Nothing to install.
search.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 search.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 search.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.
search.fetch is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). 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 →