AI agents use slack_send to create or update resources in Access — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Access environment.
slack_send creates new data (messages) that is immediately persisted and visible. While reversible (messages can be deleted), it has moderate blast radius: an agent could spam channels, leak sensitive information, or impersonate users through unintended message composition.
From the tool's definition Tool description states 'Send a Slack message to a channel, DM, or thread' with side effect of 'delivers the message immediately and it is visible to all channel members.' This is a create/post action that modifies state (adds a message to Slack) reversibly.
Attacks that exploit this kind of access
Send a Slack message to a channel, DM, or thread. Side effect: delivers the message immediately and it is visible to all channel members. Supports Slack mrkdwn formatting. It is categorised as a Write tool in the Access MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Access MCP server in PolicyLayer and add a rule for slack_send: 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 Access. Nothing to install.
slack_send 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 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. 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 is provided by the Access MCP server (scottpedia0/access). 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 →