Skip to main content
Glama
Rift Finance MCP Server

Rift Finance MCP Server

Official
by Rift-FI

rift_buy_crypto

Buy crypto (USDC or USDT) on Base, Arbitrum, Polygon, Ethereum, or Celo using local fiat through mobile money like M-Pesa. Preview the onramp rate first to see the tokens you'll receive.

Instructions

Buy crypto with mobile money (M-Pesa, etc). REAL PAYMENT — confirm with user. The 'amount' here is in LOCAL FIAT currency (e.g. 1000 = 1000 KES), NOT in USDC. Use rift_preview_exchange_rate with type='onramp' first to show how much USDC they'll get. Requires: login + merchant approval + KYC (for >$20). Does NOT require OTP. User receives a mobile money prompt on their phone.

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": {
      "shortcode": "<shortcode>",
      "amount": "<amount>",
      "chain": "<chain>",
      "asset": "<asset>",
      "mobile_network": "<mobile_network>",
      "country_code": "<country_code>"
    },
    "name": "rift_buy_crypto"
  }
}

Input Schema

NameRequiredDescriptionDefault
assetYesREQUIRED. Crypto to buy: USDC or USDT
chainYesREQUIRED. Destination chain: BASE, ARBITRUM, POLYGON, ETHEREUM, CELO
amountYesREQUIRED. Amount in LOCAL FIAT currency (e.g. 1000 for 1000 KES) — NOT in USDC
shortcodeYesREQUIRED. Payment shortcode e.g. MPESA_KE
country_codeYesCountry: KE, NG, UG, GH, ET, CD, TZ, MW, BR
mobile_networkYesNetwork: Safaricom, Airtel, MTN, Vodacom, Orange Money, Telebirr, TNM, etc

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full disclosure burden and does most of it well: it flags the irreversible real-payment nature, enumerates auth/approval/KYC gates, notes the $20 KYC threshold, and explains that the end user receives an out-of-band mobile money prompt rather than completing the flow in-tool. What it omits is post-invocation behavior — whether the call returns a pending order, how to poll it, or what a failure/decline looks like, despite rift_get_onramp_status existing as a sibling.

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

Conciseness5/5

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

Roughly five short sentences, front-loaded with the risk warning ('REAL PAYMENT — confirm with user') followed by the unit clarification, prerequisite sequence, and preconditions. There is no filler, and each clause adds a distinct operational fact.

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 a six-required-parameter money-movement tool with no annotations and no output schema, the definition covers the hard parts: authorization, KYC thresholds, currency units, and the user-side prompt. The remaining gap is the return/status story — nothing tells the agent what comes back or that rift_get_onramp_status can confirm completion — which matters because there is no output schema to fall back on.

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 description coverage is 100% and every required field already carries its own description, so the baseline is 3. The description's emphasis that 'amount' is local fiat and NOT USDC does restate the schema almost verbatim, adding reinforcement value for a high-risk unit confusion but not new semantics; the remaining five parameters (shortcode, chain, asset, mobile_network, country_code) get no elaboration beyond the schema.

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?

The opening sentence states a specific verb plus resource ('Buy crypto') and constrains the funding channel ('with mobile money (M-Pesa, etc)'), which is immediately distinguishable from a transfer tool like rift_send_crypto. The follow-up clauses further pin down the exact operation (an onramp purchase paid in local fiat) so an agent knows precisely what this tool does.

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

Usage Guidelines5/5

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

It gives an explicit prior step — call rift_preview_exchange_rate with type='onramp' first — and an explicit interaction requirement — confirm with the user because this is a REAL PAYMENT. It also names the required preconditions (login, merchant approval, KYC above $20) and rules out an expected-but-unneeded step ('Does NOT require OTP'), which is exactly the when/when-not detail an agent needs before invoking a money-moving tool.

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