views_push · Slack MCP: Risk & Policy

WHAT IT DOES

What views_push does on Slack

AI agents use views_push to create or update resources in Slack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slack environment.

WHY IT NEEDS A POLICY

Why views_push needs a policy

This tool creates or modifies UI state in Slack by pushing a view onto a stack. While reversible (views can be popped or dismissed), it modifies application state and could be misused to create misleading UI, inject content, or disrupt user experience. It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial), making Write the appropriate category.

From the tool's definition Tool name 'views_push' and description 'Push a view onto the stack of a root view' indicates modification of UI state by adding/stacking a view, which is a reversible write operation affecting Slack's interface layer.

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

views_push Rate-limited

views_push stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "views_push": {
      "limits": [
        {
          "counter": "views_push_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Slack, so you can run agents against it safely.

FAQ

Questions about views_push

What does the views_push tool do? +

Push a view onto the stack of a root view. It is categorised as a Write tool in the Slack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on views_push? +

Register the Slack MCP server in PolicyLayer and add a rule for views_push: 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 Slack. Nothing to install.

What risk level is views_push? +

views_push is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit views_push? +

Yes. Add a rate_limit block to the views_push 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.

How do I block views_push completely? +

Set action: deny in the PolicyLayer policy for views_push. 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.

What MCP server provides views_push? +

views_push is provided by the Slack MCP server (karbassi/slack-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.