teams_send · Outpost MCP: Risk & Policy

WHAT IT DOES

What teams_send does on Outpost

AI agents use teams_send to create or update resources in Outpost — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outpost environment.

WHY IT NEEDS A POLICY

Why teams_send needs a policy

This tool creates a new message artifact in Teams, a reversible write operation. Severity is medium because a misused agent could spam channels, post inappropriate content, or damage team communication—but the action is recoverable (messages can be edited/deleted). Not Execute because it doesn't run arbitrary code; not Destructive because sending messages is reversible; not Financial because no money changes hands.

From the tool's definition Tool name 'teams_send' and description 'Send a message to a Teams channel' explicitly indicate creation of new message content.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

teams_send Rate-limited

teams_send 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "teams_send": {
      "limits": [
        {
          "counter": "teams_send_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Outpost, so you can run agents against it safely.

FAQ

Questions about teams_send

What does the teams_send tool do? +

Send a message to a Teams channel. It is categorised as a Write tool in the Outpost MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on teams_send? +

Register the Outpost MCP server in PolicyLayer and add a rule for teams_send: 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 Outpost. Nothing to install.

What risk level is teams_send? +

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

Can I rate-limit teams_send? +

Yes. Add a rate_limit block to the teams_send 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 teams_send completely? +

Set action: deny in the PolicyLayer policy for teams_send. 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 teams_send? +

teams_send is provided by the Outpost MCP server (signalclaude/outpost). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.