login · A2db MCP: Risk & Policy

Q: What risk level is login?

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

WHAT IT DOES

What login does on A2db

AI agents use login to create or update resources in A2db — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A2db environment.

WHY IT NEEDS A POLICY

Why login needs a policy

This tool creates or modifies stored configuration (database connections) in a reversible manner. It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). While it handles sensitive credentials, the act of saving a connection is fundamentally a Write operation.

From the tool's definition Tool description states 'Save a database connection', which creates/stores configuration data. The tool performs a validation action (attempting a real connection) but the primary effect is persisting connection credentials.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

login 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": {
    "login": {
      "limits": [
        {
          "counter": "login_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 A2db, so you can run agents against it safely.

FAQ

Questions about login

What does the login tool do? +

Save a database connection. Validates by attempting a real connection. It is categorised as a Write tool in the A2db MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on login? +

Register the A2db MCP server in PolicyLayer and add a rule for login: 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 A2db. Nothing to install.

What risk level is login? +

Can I rate-limit login? +

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

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

login is provided by the A2db MCP server (yoselabs/a2db). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.