AI agents use slack_send_message to create or update resources in Slackxmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slackxmcp environment.
slack_send_message creates new message content in Slack conversations, which is reversible (messages can be deleted or edited). This is a Write category action. Severity is medium because an AI agent could spam channels, impersonate users, or send sensitive information to unintended recipients, but the impact is limited to message creation without financial or system-level consequences.
From the tool's definition Tool description states 'Send a plain text message to a Slack conversation', which is a create/modify action.
Attacks that exploit this kind of access
Send a plain text message to a Slack conversation, optionally into an existing thread. It is categorised as a Write tool in the Slackxmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slackx MCP server in PolicyLayer and add a rule for slack_send_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 Slackxmcp. Nothing to install.
slack_send_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 slack_send_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 slack_send_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.
slack_send_message is provided by the Slackx MCP server (vaibhavpandeyvpz/slackxmcp). 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 →