mark_conversation_read
Mark all unread inbound messages in a conversation as read.
This record as markdown: /tools/io-github-polnikale-sequenzy-mcp/mark-conversation-read.md
What mark_conversation_read does on Sequenzy Mcp
AI agents use mark_conversation_read to create or update resources in Sequenzy Mcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sequenzy Mcp environment.
Why mark_conversation_read is rated Medium
This tool modifies message state without irreversibly deleting data or executing external operations. The change is reversible (messages can be marked unread again) and affects only metadata, making it a Write-category action. Severity is low because marking messages as read has minimal blast radius and no impact on data integrity, financial systems, or critical operations.
From the tool's definition Tool marks messages as read, which modifies the read/unread status of inbound messages. The verb 'mark' combined with a state change (unread → read) indicates a write operation that changes message metadata.
Attacks that exploit this kind of access
The rule that runs mark_conversation_read safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sequenzy Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mark_conversation_read, this is the rule to start with:
mark_conversation_read 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 Sequenzy Mcp, apply this rule, and every mark_conversation_read call is checked against it from then on.
Questions about mark_conversation_read
Mark all unread inbound messages in a conversation as read. It is categorised as a Write tool in the Sequenzy Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sequenzy MCP server in PolicyLayer and add a rule for mark_conversation_read: 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 Sequenzy Mcp. Nothing to install.
mark_conversation_read 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 mark_conversation_read 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 mark_conversation_read. 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.
mark_conversation_read is provided by the Sequenzy MCP server (Sequenzy/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sequenzy, and thousands of servers like it.
This server
Across the catalogue