configure_credentials · LibreLink MCP Server MCP

WHAT IT DOES

What configure_credentials does on LibreLink MCP Server

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

WHY IT NEEDS A POLICY

Why configure_credentials needs a policy

This tool modifies sensitive authentication state by storing or updating credentials in the system keychain. While not destructive (credentials can be reconfigured), it is a Write operation that creates/updates security-critical data. Severity is high because compromised credential storage could enable unauthorized access to personal health data (glucose readings).

From the tool's definition Tool performs 'Set up or update your LibreLinkUp account credentials' - explicitly creates or modifies stored authentication data. The description emphasizes credential storage with encryption, indicating persistent state modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

configure_credentials Rate-limited

configure_credentials 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": {
    "configure_credentials": {
      "limits": [
        {
          "counter": "configure_credentials_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 LibreLink MCP Server, so you can run agents against it safely.

FAQ

Questions about configure_credentials

What does the configure_credentials tool do? +

Set up or update your LibreLinkUp account credentials for data access. Required before using any glucose reading tools. Credentials are stored securely using AES-256-GCM encryption with keys in your OS keychain. It is categorised as a Write tool in the LibreLink MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on configure_credentials? +

Register the LibreLink MCP Server MCP server in PolicyLayer and add a rule for configure_credentials: 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 LibreLink MCP Server. Nothing to install.

What risk level is configure_credentials? +

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

Can I rate-limit configure_credentials? +

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

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

configure_credentials is provided by the LibreLink MCP Server MCP server (sedoglia/librelink-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.