This record as markdown: /tools/karbassi-slack-mcp/conversations-mark.md
What conversations_mark does on Slack
AI agents use conversations_mark 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 conversations_mark is rated Medium
This tool modifies cursor position state in Slack channels, which is a reversible write operation. While not destructive, it alters user-visible application state. Severity is medium because misuse could disrupt user experience by masking unread messages or creating false impression of message consumption, but the effect is reversible and non-permanent.
From the tool's definition Tool name 'conversations_mark' combined with description 'Set the read cursor in a channel' indicates modification of user state (read position) rather than data retrieval.
Attacks that exploit this kind of access
The rule that runs conversations_mark 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 conversations_mark, this is the rule to start with:
conversations_mark 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 conversations_mark call is checked against it from then on.
Questions about conversations_mark
Set the read cursor in a channel. 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 conversations_mark: 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.
conversations_mark 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 conversations_mark 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 conversations_mark. 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.
conversations_mark 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