Flag, unflag, or mark a message as complete. Flagged messages appear in the flagged email view.
AI agents use outlook_flag_message to create or update resources in Sage MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sage MCP environment.
This tool modifies message metadata (flag status) in Outlook, which is a reversible write operation. It does not delete data, execute code, or involve financial transactions. The action can be undone by unflagging, making it a Write category. Medium severity because misuse could affect email organization and task tracking for potentially many messages across a multi-tenant platform.
From the tool's definition Flag, unflag, or mark a message as complete. Flagged messages appear in the flagged email view.
Documented attack patterns abuse exactly the kind of access outlook_flag_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sage MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for outlook_flag_message:
{
"version": "1",
"default": "deny",
"tools": {
"outlook_flag_message": {
"limits": [
{
"counter": "outlook_flag_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}outlook_flag_message 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.
Flag, unflag, or mark a message as complete. Flagged messages appear in the flagged email view. It is categorised as a Write tool in the Sage MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sage MCP server in PolicyLayer and add a rule for outlook_flag_message: 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 Sage MCP. Nothing to install.
outlook_flag_message 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 outlook_flag_message 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 outlook_flag_message. 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.
outlook_flag_message is provided by the Sage MCP server (sagemcp/sagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 359 Sage MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
359 Sage MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.