AI agents use mark_conversation_unread to create or update resources in Canvas MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Canvas MCP Server environment.
This tool modifies data (conversation read status) in a reversible manner. It is not destructive (the conversation is not deleted), not financial, and not code execution. It is a straightforward write operation that changes metadata about a conversation. The impact is minimal—affecting only the user's interface state for organizing conversations—making it low severity.
From the tool's definition Tool name 'mark_conversation_unread' and description 'Mark a conversation as unread' indicate a state modification operation that changes the read/unread status of a conversation.
Documented attack patterns abuse exactly the kind of access mark_conversation_unread gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Canvas MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mark_conversation_unread:
{
"version": "1",
"default": "deny",
"tools": {
"mark_conversation_unread": {
"limits": [
{
"counter": "mark_conversation_unread_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark_conversation_unread 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.
Free to start. No card required.
Mark a conversation as unread. It is categorised as a Write tool in the Canvas MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Canvas MCP Server MCP server in PolicyLayer and add a rule for mark_conversation_unread: 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 Canvas MCP Server. Nothing to install.
mark_conversation_unread 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_unread 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_unread. 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_unread is provided by the Canvas MCP Server MCP server (plyght/canvas-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Canvas MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 Canvas MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.