check_connection
AI agents call check_connection to retrieve information from ntropy-mcp MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
A connection check typically queries status without modifying or executing operations on data. However, the empty description reduces confidence. Given the sibling tools include destructive operations (delete_account_holder, delete_transaction), this tool's minimal name suggests it is a benign diagnostic utility—most likely a Read operation that verifies API availability.
From the tool's definition Tool name 'check_connection' suggests a simple connectivity verification with no side effects. Description is empty, limiting definitive classification.
Attacks that exploit this kind of access
check_connection. It is categorised as a Read tool in the ntropy-mcp MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ntropy-mcp MCP Server MCP server in PolicyLayer and add a rule for check_connection: 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 ntropy-mcp MCP Server. Nothing to install.
check_connection 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 check_connection 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 check_connection. 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.
check_connection is provided by the ntropy-mcp MCP Server MCP server (ntropy-network/ntropy-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 →