Search Mundi Morgado
AI agents call links_search to retrieve information from Mundigital without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only search operation over a public professional profile. It queries and retrieves data without side effects, modifications, or irreversible changes. The minimal description ('Search Mundi Morgado') combined with the server's read-only nature and sibling tools (brief, fetch, links_fetch, search) all performing retrieval operations confirms this belongs in the Read category with low severity due to…
From the tool's definition Tool is described as 'Search' which retrieves data; server context emphasizes 'read-only professional profile' and 'search resume evidence'; no mutation or deletion capabilities mentioned.
Attacks that exploit this kind of access
Search Mundi Morgado. It is categorised as a Read tool in the Mundigital MCP Server, which means it retrieves data without modifying state.
Register the Mundigital MCP server in PolicyLayer and add a rule for links_search: 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 Mundigital. Nothing to install.
links_search 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 links_search 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 links_search. 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.
links_search is provided by the Mundigital MCP server (mundizzle/mun.digital). 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 →