map_links
AI agents call map_links to retrieve information from MD Webcrawl MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to map or enumerate links from a crawled website, which is a read-only operation that retrieves information about site structure. Despite the description being empty, the context of a web crawling server focused on content extraction and the tool's name strongly suggest it queries link relationships without modifying or executing anything.
From the tool's definition Tool name 'map_links' combined with server context indicating website structure mapping and link extraction. The server is designed to crawl and extract content with no destructive, financial, or execution capabilities mentioned.
Attacks that exploit this kind of access
map_links. It is categorised as a Read tool in the MD Webcrawl MCP MCP Server, which means it retrieves data without modifying state.
Register the MD Webcrawl MCP server in PolicyLayer and add a rule for map_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 MD Webcrawl MCP. Nothing to install.
map_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 map_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 map_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.
map_links is provided by the MD Webcrawl MCP server (jmh108/md-webcrawl-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 →