Skip to main content
Glama
Rift Finance MCP Server

Rift Finance MCP Server

Official
by Rift-FI

rift_login_google

Authenticate or create a Rift Finance account using a Google ID token, then access all authenticated tools. Obtain the token from the user's Google identity flow before calling.

Instructions

Sign in (or sign up on first use) with a Google ID token. The frontend obtains the idToken from Google's identity flow — for example, the credential from Google One-Tap, or an ID token from useGoogleLogin({ flow: 'implicit' }) exchanged via Google's OAuth2 endpoint. NOT something the agent can produce on its own — ask the user / client for the idToken. Once an account is bound to Google, password/OTP login is rejected for that account; the user must keep using Google. After this call, all authenticated tools work.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "idToken": "<idToken>"
    },
    "name": "rift_login_google"
  }
}

Input Schema

NameRequiredDescriptionDefault
idTokenYesGoogle ID token (JWT) obtained on the frontend from Google's identity flow
referrerNoOptional referral code — propagated to the new user only on first sign-in (account creation)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.0

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does substantial work: it discloses that first use creates an account, that Google binding permanently disables password/OTP login, and that successful auth unlocks all authenticated tools. It omits what the call returns (session token shape/expiry), which matters for a login tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the action, then the token-acquisition caveat, then the account-binding consequence and outcome — a sensible order. The Google One-Tap / useGoogleLogin examples are somewhat verbose but earn their place by telling the agent exactly what to ask the user for.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an unannotated, output-schema-less login tool this is close to complete: credential source, agent limitation, irreversible binding behavior, and the post-call state are all covered. The main gap is the return value, which nothing else in the definition supplies.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are already documented. The description adds real-world provenance for idToken (One-Tap `credential`, `useGoogleLogin` implicit flow), but its referrer note largely repeats the schema's 'propagated to the new user only on first sign-in.' Baseline 3 fits.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Sign in ... with a Google ID token') and adds the first-use signup case. The 'Google' qualifier cleanly separates it from password/OTP login and the Apple variant, so an agent can pick it without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operating context: the idToken comes from the frontend's Google identity flow and is 'NOT something the agent can produce on its own — ask the user / client.' That is actionable routing guidance. It does not explicitly contrast with rift_login_apple or rift_login, leaving the sibling choice to the obvious provider name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools