get_client_mrr
AI agents call get_client_mrr to retrieve information from ConnectWise Live MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves financial metrics (MRR) about a client without modifying, deleting, or committing financial transactions. While it accesses financial data, the action is passive data retrieval, classifying it as Read rather than Financial. The empty description reduces confidence slightly, but the naming convention is clear.
From the tool's definition Tool name 'get_client_mrr' indicates retrieval of Monthly Recurring Revenue data for a client. The 'get_' prefix and lack of modification language strongly suggest a read operation. Description is empty, limiting full certainty.
Attacks that exploit this kind of access
get_client_mrr. It is categorised as a Read tool in the ConnectWise Live MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ConnectWise Live MCP Server MCP server in PolicyLayer and add a rule for get_client_mrr: 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 ConnectWise Live MCP Server. Nothing to install.
get_client_mrr 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_client_mrr 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_client_mrr. 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_client_mrr is provided by the ConnectWise Live MCP Server MCP server (mfrostbutter/connectwise-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 →