Send a direct message to a member
AI agents use dooray_send_direct_message to create or update resources in Dooray MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dooray MCP Server environment.
This tool creates new data (a direct message) that is reversible—messages can typically be deleted or edited in modern collaboration platforms. It modifies state by adding a new message record but does not permanently destroy data, execute code, move money, or trigger external system commands.
From the tool's definition Tool performs 'Send a direct message' action, which creates new message data in the Dooray system with side effects on communication channels.
Attacks that exploit this kind of access
Send a direct message to a member. It is categorised as a Write tool in the Dooray MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dooray MCP Server MCP server in PolicyLayer and add a rule for dooray_send_direct_message: 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 Dooray MCP Server. Nothing to install.
dooray_send_direct_message 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 dooray_send_direct_message 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 dooray_send_direct_message. 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.
dooray_send_direct_message is provided by the Dooray MCP Server MCP server (kwanok/dooray-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 →