This record as markdown: /tools/karbassi-slack-mcp/search-save.md
What search_save does on Slack
AI agents use search_save 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 search_save is rated Medium
The name 'search_save' implies persisting or saving a search query or configuration, which is a Write operation. However, the empty description significantly lowers confidence. It could also be Read if it merely saves state client-side, but saving data to a server is the most likely interpretation given the Slack MCP context.
From the tool's definition Tool name 'search_save' suggests saving a search; description is empty and uninformative.
Attacks that exploit this kind of access
The rule that runs search_save 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 search_save, this is the rule to start with:
search_save 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Slack, apply this rule, and every search_save call is checked against it from then on.
Questions about search_save
search_save is a write tool on the Slack MCP server. 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 search_save: 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.
search_save 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 search_save 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 search_save. 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.
search_save 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.
This server
Across the catalogue