read-credential

What read-credential does on Frontmcp

AI agents call read-credential to retrieve information from Frontmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why read-credential is rated Low

This tool retrieves credential data, which is a read operation with no side effects on data state. However, severity is elevated to 'high' rather than 'low' because credentials are sensitive authentication material; an AI agent with unrestricted access could exfiltrate secrets or tokens, creating significant security risk even though the operation itself is non-destructive.

From the tool's definition Tool name explicitly states 'read-credential' and description confirms it 'Read[s] a per-session credential'. The verb 'read' and absence of any modification semantics clearly indicate a retrieval operation.

The rule that runs read-credential safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Frontmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For read-credential, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "read-credential": {}
  }
}

Questions about read-credential