swit-oauth-start · Swit MCP Server MCP: Risk & Policy

WHAT IT DOES

What swit-oauth-start does on Swit MCP Server

AI agents invoke swit-oauth-start to trigger actions in Swit MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why swit-oauth-start needs a policy

This tool initiates OAuth authentication, which is an external operation that redirects to a browser and has side effects (establishes authentication state, credentials, and session context). While not destructive or financial, it qualifies as Execute because it triggers an external operation whose effects depend on user interaction and the authentication service response.

From the tool's definition Tool name: 'swit-oauth-start'. Description states it 'Start OAuth authentication' and 'Returns authentication URL that can be opened in browser.' This initiates an external authentication flow via browser, which is an action that triggers external operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

swit-oauth-start Rate-limited

swit-oauth-start stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "swit-oauth-start": {
      "limits": [
        {
          "counter": "swit-oauth-start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about swit-oauth-start

What does the swit-oauth-start tool do? +

Start OAuth authentication. Returns authentication URL that can be opened in browser. It is categorised as a Execute tool in the Swit MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on swit-oauth-start? +

Register the Swit MCP Server MCP server in PolicyLayer and add a rule for swit-oauth-start: 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 Swit MCP Server. Nothing to install.

What risk level is swit-oauth-start? +

swit-oauth-start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit swit-oauth-start? +

Yes. Add a rate_limit block to the swit-oauth-start 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 swit-oauth-start completely? +

Set action: deny in the PolicyLayer policy for swit-oauth-start. 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 swit-oauth-start? +

swit-oauth-start is provided by the Swit MCP Server MCP server (tykann/swit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.