AI agents call org_search to retrieve information from NetworksDB-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
org_search queries and retrieves organization data based on name input—a read-only lookup operation. No creation, modification, deletion, code execution, or financial impact is possible. Severity is low as organization search results are typically public information with minimal risk if misused.
From the tool's definition Tool retrieves organization information via search query. Sibling tools indicate this server performs lookups (asn_info, dns, ip_geo, ip_info, reverse_dns, org_info) with no mutation capability mentioned.
Documented attack patterns abuse exactly the kind of access org_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and NetworksDB-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for org_search:
{
"version": "1",
"default": "deny",
"tools": {
"org_search": {}
}
}org_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for organizations by name. It is categorised as a Read tool in the NetworksDB-MCP MCP Server, which means it retrieves data without modifying state.
Register the NetworksDB- MCP server in PolicyLayer and add a rule for org_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 NetworksDB-MCP. Nothing to install.
org_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 org_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 org_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.
org_search is provided by the NetworksDB- MCP server (mordavid/networksdb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from NetworksDB-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 NetworksDB-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.