Fetch content from a Tor/onion service URL
AI agents call tor_fetch to retrieve information from Tor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves content from remote URLs via Tor without creating, modifying, or deleting data. However, severity is elevated to 'medium' because: (1) Tor/onion services are associated with potentially malicious or illegal content despite the server's stated 'safety guardrails'; (2) fetching unvetted content could expose the system to malware, exploits, or harmful payloads; (3) an AI agent with unconstrained use…
From the tool's definition Tool name 'tor_fetch' and description 'Fetch content from a Tor/onion service URL' indicate retrieval/querying of data with no modification or deletion. The word 'fetch' is a classic Read operation.
Attacks that exploit this kind of access
Fetch content from a Tor/onion service URL. It is categorised as a Read tool in the Tor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Tor MCP Server MCP server in PolicyLayer and add a rule for tor_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 Tor MCP Server. Nothing to install.
tor_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 tor_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 tor_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.
tor_fetch is provided by the Tor MCP Server MCP server (pjv4yj/tor-mcp-server). 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 →