discover_links
AI agents call discover_links to retrieve information from FetchV2 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 link metadata from web pages without modifying, deleting, or executing any code. It is purely informational and has minimal blast radius if misused by an AI agent—worst case being crawling unexpected URLs or mapping unexpected link structures. No financial, destructive, or execute-class operations are involved.
From the tool's definition Tool name 'discover_links' and server description indicating the server 'discover links' as a capability. The FetchV2 MCP Server is designed for 'web content fetching and extraction' with no mention of modifying, deleting, or executing operations.
Attacks that exploit this kind of access
discover_links. It is categorised as a Read tool in the FetchV2 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FetchV2 MCP Server MCP server in PolicyLayer and add a rule for discover_links: 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 FetchV2 MCP Server. Nothing to install.
discover_links 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 discover_links 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 discover_links. 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.
discover_links is provided by the FetchV2 MCP Server MCP server (praveenc/fetchv2-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 →