fetch
AI agents call fetch to retrieve information from Free Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Fetching pages and documents is a retrieval operation with no data modification, deletion, or execution of arbitrary code. It is a straightforward Read operation. Confidence is 0.85 rather than higher because the tool description itself is empty, leaving some ambiguity, but the server context and sibling tools (research, extract_structured) strongly suggest this is a document/page retrieval function.
From the tool's definition Tool named 'fetch' on a server described as enabling LLMs to 'fetch pages' and 'read documents'. The server description emphasizes search, fetch, and read operations with 'no side effects' implied by the local-first, read-only nature of web searching and…
Attacks that exploit this kind of access
fetch. It is categorised as a Read tool in the Free Search MCP Server, which means it retrieves data without modifying state.
Register the Free Search 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 Free Search. 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 Free Search MCP server (sweetcornna/free-search-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 →