AI agents use create_chat_user to create or update resources in Sendbird — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sendbird environment.
This tool creates new data (user account and access token) in a reversible manner. It does not delete, destroy, or execute arbitrary code. While it has security implications (issuing auth tokens), the action is Write-category as it creates new entities.
From the tool's definition Tool description states it will 'Provision a new chat user ID and profile' and 'Returns the user_id and an access_token', indicating creation of new user records and authentication credentials.
Attacks that exploit this kind of access
Provision a new chat user ID and profile in the Sendbird application. Returns the user_id and an access_token for client SDK auth. It is categorised as a Write tool in the Sendbird MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sendbird MCP server in PolicyLayer and add a rule for create_chat_user: 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 Sendbird. Nothing to install.
create_chat_user 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_chat_user 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_chat_user. 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_chat_user is provided by the Sendbird MCP server (nobanks/sendbird-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 →