Steward MCP

Overview Schema Source Related Servers Discussions Admin

steward_fx

Convert fiat amounts across ISO 4217 currencies at current reference rates for pricing, payouts, or multi-currency accounting; rates are references, not execution quotes.

Instructions

Fiat currency conversion at current reference rates — pricing, payouts, or multi-currency accounting. Reference rates only, not execution quotes; for crypto transfer fees use steward_cheapest_route instead. Paid: $0.01 USDC on Base per call — the rail quotes each call via 402; this server verifies the quote (exact scheme, Base network, USDC, Steward payee) and settles from your wallet automatically, refusing quotes over your per-call or daily spend caps. Your payer key never leaves your machine.

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": {
      "amount": "<amount>",
      "from": "<from>",
      "to": "<to>"
    },
    "name": "steward_fx"
  }
}

Input Schema

Name	Required	Description
`to`	Yes	Target currency as a 3-letter ISO 4217 code, e.g. EUR. Case-insensitive; uppercased automatically.
`from`	Yes	Source currency as a 3-letter ISO 4217 code, e.g. USD. Case-insensitive; uppercased automatically.
`amount`	Yes	Amount to convert, must be positive (e.g. 99.99).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Oct 17, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the price ($0.01 USDC on Base per call), the 402 quote-and-settle flow, the exact verification criteria (scheme, network, token, payee), spend-cap enforcement, and the security property that the payer key never leaves the machine. This is far beyond a bare 'convert currency' statement.

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-loaded with purpose, then routing guidance, then payment mechanics — a sensible order. The payment sentence is dense but every clause (cost, rail, verification, caps, key safety) earns its place; only minor tightening is possible.

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?

Payment, routing, and scoping are covered thoroughly. With no output schema, the description leaves the return shape (converted amount, applied rate, timestamp) unspecified, which is the one remaining gap for a conversion tool.

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%, so the schema already documents amount, from, and to with format, case handling, and positivity constraints. The description adds no parameter-level detail beyond that, which is the expected baseline when the schema does the heavy lifting.

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 ('Fiat currency conversion at current reference rates') plus concrete use cases (pricing, payouts, multi-currency accounting). It also explicitly distinguishes itself from the sibling steward_cheapest_route, so an agent can route 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 Guidelines5/5

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

Gives both a when-to-use ('pricing, payouts, or multi-currency accounting'), a when-not ('Reference rates only, not execution quotes'), and the named alternative for the excluded case ('for crypto transfer fees use steward_cheapest_route instead'). Nothing is left to inference.

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