Generate a launch URL for a Tough Customer roleplay on a Salesforce
AI agents use create_roleplay_session to create or update resources in Tough Customer MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tough Customer MCP environment.
The tool creates a new roleplay session and generates a launch URL, which is a Write operation (creating a new resource/record). It operates on Salesforce data, which could have broader implications if misconfigured, but there's no indication of destructive, financial, or code-execution behavior.
From the tool's definition Generate a launch URL for a Tough Customer roleplay on a Salesforce
Attacks that exploit this kind of access
Generate a launch URL for a Tough Customer roleplay on a Salesforce. It is categorised as a Write tool in the Tough Customer MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tough Customer MCP server in PolicyLayer and add a rule for create_roleplay_session: 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 Tough Customer MCP. Nothing to install.
create_roleplay_session 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 create_roleplay_session 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 create_roleplay_session. 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.
create_roleplay_session is provided by the Tough Customer MCP server (toughcustomerai/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 →