fidelity_login · Claude Fidelity MCP: Risk & Policy

WHAT IT DOES

What fidelity_login does on Claude Fidelity

AI agents invoke fidelity_login to trigger actions in Claude Fidelity. 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 fidelity_login needs a policy

This tool uses Playwright browser automation to authenticate into a financial brokerage account. While login itself is not directly Financial or Destructive, it is an Execute-category action (triggers external browser operations) that establishes the session enabling all subsequent financial operations (trading, order placement, account management).

From the tool's definition Log in to Fidelity. Supports TOTP 2FA (automatic) and SMS 2FA (requires follow-up with fidelity_submit_2fa). Credentials can be passed directly or via env vars FIDELITY_USERNAME, FIDELITY_PASSWORD, FIDELITY_TOTP_SECRET.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

fidelity_login Rate-limited

fidelity_login 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": {
    "fidelity_login": {
      "limits": [
        {
          "counter": "fidelity_login_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 Claude Fidelity, so you can run agents against it safely.

FAQ

Questions about fidelity_login

What does the fidelity_login tool do? +

Log in to Fidelity. Supports TOTP 2FA (automatic) and SMS 2FA (requires follow-up with fidelity_submit_2fa). Credentials can be passed directly or via env vars FIDELITY_USERNAME, FIDELITY_PASSWORD, FIDELITY_TOTP_SECRET. It is categorised as a Execute tool in the Claude Fidelity MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on fidelity_login? +

Register the Claude Fidelity MCP server in PolicyLayer and add a rule for fidelity_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 Claude Fidelity. Nothing to install.

What risk level is fidelity_login? +

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

Can I rate-limit fidelity_login? +

Yes. Add a rate_limit block to the fidelity_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 fidelity_login completely? +

Set action: deny in the PolicyLayer policy for fidelity_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 fidelity_login? +

fidelity_login is provided by the Claude Fidelity MCP server (tylerflar/claude-fidelity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.