List available tax codes. Use when creating or updating quotes that require tax assignment.
AI agents call get_tax_codes to retrieve information from Connectwise Sell without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and lists tax code data for reference purposes during quote creation/updates. It performs a read-only query without creating, modifying, deleting, or executing any operations. The blast radius is minimal—worst case, an agent reads tax code information it shouldn't have access to, but no data is altered or external operations triggered.
From the tool's definition Tool name is 'get_tax_codes' and description states 'List available tax codes'. This is a retrieval operation with no side effects.
Attacks that exploit this kind of access
List available tax codes. Use when creating or updating quotes that require tax assignment. It is categorised as a Read tool in the Connectwise Sell MCP Server, which means it retrieves data without modifying state.
Register the Connectwise Sell MCP server in PolicyLayer and add a rule for get_tax_codes: 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 Sell. Nothing to install.
get_tax_codes 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_tax_codes 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_tax_codes. 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_tax_codes is provided by the Connectwise Sell MCP server (mfrostbutter/connectwise-sell-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 →