fetch
AI agents call fetch to retrieve information from Server Everything without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'fetch' indicates data retrieval with no side effects. However, the empty description prevents higher confidence assessment. Given the sibling tools on this server include write/execute/destructive operations (create_directory, edit_file, delete_entities), this 'fetch' tool most likely retrieves or queries data. Without explicit evidence, confidence is moderate (0.7) rather than high.
From the tool's definition Tool name 'fetch' typically retrieves data without modification. Description is empty, which reduces confidence, but conventional naming suggests a read operation.
Attacks that exploit this kind of access
fetch. It is categorised as a Read tool in the Server Everything MCP Server, which means it retrieves data without modifying state.
Register the Server Everything 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 Server Everything. 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 Server Everything MCP server (@modelcontextprotocol/server-everything). 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 →