AI agents use update_relationship to create or update resources in Smokeball — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Smokeball environment.
This tool modifies contact relationships within matters, which is a write operation that changes data state but can be reversed (relationships can be re-updated or removed). It does not delete data (Destructive), execute code (Execute), involve money movements (Financial), or retrieve information only (Read).
From the tool's definition Tool name 'update_relationship' and description 'Update a contact relationship on a matter role' indicate modification of existing data.
Attacks that exploit this kind of access
Update a contact relationship on a matter role. It is categorised as a Write tool in the Smokeball MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Smokeball MCP server in PolicyLayer and add a rule for update_relationship: 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.
update_relationship is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_relationship 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 update_relationship. 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.
update_relationship 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 →