Build a network graph centered on an insider or company, showing all connected entities. Reveals the web of insider relationships.
AI agents call get_insider_network to retrieve information from Lynx Mi/lynx Mi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing data about insider relationships and network connections. It performs analysis and graph construction but does not create, modify, delete, or execute external operations.
From the tool's definition Tool name 'get_insider_network' and description 'Build a network graph centered on an insider or company, showing all connected entities.
Attacks that exploit this kind of access
Build a network graph centered on an insider or company, showing all connected entities. Reveals the web of insider relationships. It is categorised as a Read tool in the Lynx Mi/lynx Mi MCP Server, which means it retrieves data without modifying state.
Register the Lynx Mi/lynx Mi MCP server in PolicyLayer and add a rule for get_insider_network: 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 Lynx Mi/lynx Mi. Nothing to install.
get_insider_network 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 get_insider_network 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 get_insider_network. 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.
get_insider_network is provided by the Lynx Mi/lynx Mi MCP server (lynx-mi/lynx-mi-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 →