Medium Risk

outlook_send_message

Send a new email message. Supports HTML and text body content, with CC and BCC recipients.

How to control outlook_send_message ↓

AI agents use outlook_send_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.

Medium Risk

Sending an email is a write operation that creates a new message in the recipient's mailbox. While reversible in some email systems (can be recalled/deleted in limited cases), the primary effect is creation of new data/communication that has been delivered. The ability to send to CC/BCC recipients and use HTML content increases the potential for misuse (phishing, spam, social engineering).

From the tool's definition Tool description states 'Send a new email message' with support for 'HTML and text body content, with CC and BCC recipients.' This creates new email records irreversibly.

Documented attack patterns abuse exactly the kind of access outlook_send_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_send_message:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "outlook_send_message": {
      "limits": [
        {
          "counter": "outlook_send_message_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

outlook_send_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.

  1. Create a free account and register Sage MCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the outlook_send_message tool do? +

Send a new email message. Supports HTML and text body content, with CC and BCC recipients. 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.

How do I enforce a policy on outlook_send_message? +

Register the Sage MCP server in PolicyLayer and add a rule for outlook_send_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.

What risk level is outlook_send_message? +

outlook_send_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit outlook_send_message? +

Yes. Add a rate_limit block to the outlook_send_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.

How do I block outlook_send_message completely? +

Set action: deny in the PolicyLayer policy for outlook_send_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.

What MCP server provides outlook_send_message? +

outlook_send_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.

Enforce policy on every Sage MCP tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.