This record as markdown: /tools/karbassi-slack-mcp/views-open.md
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 views_open is rated High
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
The rule that runs views_open safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Slack, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For views_open, this is the rule to start with:
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.
The button opens the PolicyLayer dashboard: create your workspace, connect Slack, apply this rule, and every views_open call is checked against it from then on.
Questions about views_open
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.
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.
views_open is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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.
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.
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.
More on Slack, and thousands of servers like it.
Across the catalogue