start_gitlab_auth · Activity Collector MCP: Risk & Policy

WHAT IT DOES

What start_gitlab_auth does on Activity Collector MCP

AI agents invoke start_gitlab_auth to trigger actions in Activity Collector MCP. 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 start_gitlab_auth needs a policy

This tool executes a browser action to initiate OAuth authentication, which is an external operation triggering the browser and managing authentication state. While not destructive or financial, it goes beyond simple data retrieval (Read) or reversible modification (Write). It falls under Execute because it launches processes and manages authentication flows.

From the tool's definition Tool opens a browser and manages OAuth authentication flow (returns authorization code). This triggers an external operation (browser launch) whose effects depend on user interaction and subsequent authentication state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_gitlab_auth Rate-limited

start_gitlab_auth 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": {
    "start_gitlab_auth": {
      "limits": [
        {
          "counter": "start_gitlab_auth_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 Activity Collector MCP, so you can run agents against it safely.

FAQ

Questions about start_gitlab_auth

What does the start_gitlab_auth tool do? +

Step 1: Start GitLab OAuth authentication. Opens browser and returns authorization code. Fast and reliable. It is categorised as a Execute tool in the Activity Collector MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_gitlab_auth? +

Register the Activity Collector MCP server in PolicyLayer and add a rule for start_gitlab_auth: 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 Activity Collector MCP. Nothing to install.

What risk level is start_gitlab_auth? +

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

Can I rate-limit start_gitlab_auth? +

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

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

start_gitlab_auth is provided by the Activity Collector MCP server (srdmathur/activity-collector-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.