AI agents call get_relationships_on_matter to retrieve information from Smokeball without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing relationship data associated with a matter. The verb 'get' and lack of any modification language (create, update, delete) clearly indicate a read-only operation. The blast radius of unauthorized access is limited to information disclosure about contact relationships, which is low risk compared to financial, destructive, or executable operations.
From the tool's definition Tool name 'get_relationships_on_matter' and description 'Get all contact relationships on a matter' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get all contact relationships on a matter. It is categorised as a Read tool in the Smokeball MCP Server, which means it retrieves data without modifying state.
Register the Smokeball MCP server in PolicyLayer and add a rule for get_relationships_on_matter: 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 Smokeball. Nothing to install.
get_relationships_on_matter 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_relationships_on_matter 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_relationships_on_matter. 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_relationships_on_matter is provided by the Smokeball MCP server (rosenadvertising/smokeball-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 →