AI agents use saved_add 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.
The 'add' action is reversible (items can be unsaved), making this a Write rather than Destructive operation. Severity is high because saved items are often used to organize sensitive or important information; misuse could result in unwanted bookmarking of confidential conversations, files, or other Slack objects.
From the tool's definition Tool name 'saved_add' indicates adding to saved items. In the context of a Slack MCP server with 'full access to Slack: messages, channels, files, canvases, lists', this tool creates or modifies saved items (e.g., saving messages, files, or other Slack…
Attacks that exploit this kind of access
saved_add. 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.
Register the Slack MCP server in PolicyLayer and add a rule for saved_add: 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.
saved_add 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 saved_add 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 saved_add. 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.
saved_add 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.
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 →