views_open · Slack MCP: Risk & Policy

WHAT IT DOES

What views_open does on Slack

AI agents invoke views_open to trigger actions in Slack. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why views_open needs a policy

Opening a view is an external operation that affects the Slack UI for a user (e.g., opening a modal or app surface). It is not a simple read, nor does it write/delete data, but it does trigger an external interactive operation in the Slack platform whose effects depend on arguments (which view, which user). This places it in Execute.

From the tool's definition 'Open a view for a user' — triggers an external UI operation in Slack's interface for a specific user

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

views_open Rate-limited

views_open stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_open": {
      "limits": [
        {
          "counter": "views_open_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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_open

What does the views_open tool do? +

Open a view for a user. It is categorised as a Execute tool in the Slack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on views_open? +

Register the Slack MCP server in PolicyLayer and add a rule for views_open: 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_open? +

views_open is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit views_open? +

Yes. Add a rate_limit block to the views_open 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_open completely? +

Set action: deny in the PolicyLayer policy for views_open. 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_open? +

views_open 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.