# Foundry: prepaid AI compute in USDF (remote · api.usdf.fi)

Prepaid AI compute in USDF: models, quotes and chat with a receipt; pay per call (x402) or by key

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- remote · `api.usdf.fi`: 73/100 (this document), [markdown](https://verifymcp.io/servers/fi-usdf-gateway/api.md), [page](https://verifymcp.io/servers/fi-usdf-gateway/api)

## Channel facts

- Endpoint: `https://api.usdf.fi/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-22.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2163 tokens (~216/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Foundry: prepaid AI compute in USDF MCP server?

Foundry: prepaid AI compute in USDF is a hosted endpoint at https://api.usdf.fi/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http fi-usdf-gateway 'https://api.usdf.fi/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "fi-usdf-gateway": {
      "url": "https://api.usdf.fi/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fi-usdf-gateway": {
      "type": "http",
      "url": "https://api.usdf.fi/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.fi-usdf-gateway]
url = "https://api.usdf.fi/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fi-usdf-gateway": {
      "type": "remote",
      "url": "https://api.usdf.fi/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add fi-usdf-gateway --url 'https://api.usdf.fi/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  fi-usdf-gateway:
    url: "https://api.usdf.fi/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "fi-usdf-gateway": {
      "Transport": "http",
      "Url": "https://api.usdf.fi/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add fi-usdf-gateway -t streamable-http -u 'https://api.usdf.fi/mcp'
```

### Other

```json
{
  "mcpServers": {
    "fi-usdf-gateway": {
      "type": "http",
      "url": "https://api.usdf.fi/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-21 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 72, 0)

- [security] Tool “balance” rewrote its description, which is the text the model reads
- [security] Tool “chat” rewrote its description, which is the text the model reads

### 2026-10-19 (score 72, +1)

- [cosmetic] “x402_pay” reworded the description of “network”

### 2026-10-18 (score 71, 0)

- [security] Tool “agents_market_call” rewrote its description, which is the text the model reads
- [security] Tool “balance” rewrote its description, which is the text the model reads
- [security] Tool “chat” rewrote its description, which is the text the model reads
- [security] Tool “list_tools” rewrote its description, which is the text the model reads
- [security] Tool “quote_tool” rewrote its description, which is the text the model reads
- [security] Tool “receipt” rewrote its description, which is the text the model reads
- [security] Tool “x402_pay” rewrote its description, which is the text the model reads

### 2026-10-17 (score 71, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-16 (score 70)

First indexed and scored.

## MCP tools (10)

### `list_models` (~48 tokens)

List models

Models the gateway serves with their prices (USD per 1M tokens, the same figure in USDF), context window, output limits and whether a route is available right now. No key needed.

### `quote` (~233 tokens)

Quote a request

The hold the chat tool places before running a request, in USDF and USD (output capped at 4096 tokens). It is an estimate, not a ceiling: a completed request is billed the provider's reported usage, normally less. Pass prompt or messages. No key needed; a request for attested hardware (a :private model id or provider.private), and any request from a Private-tier key, is quoted on its attested routes, at the model's price.

Input parameters:

- `max_tokens` (number): Output token budget, a positive integer; defaults to the model's default_max_output, capped at max_output
- `messages` (array): Chat messages in the OpenAI format: objects with a role (system, user, assistant or tool) and content (text, or an array of content parts)
- `model` (string, required): Model id from list_models
- `prompt` (string): Prompt text, sent as one user message
- `provider` (object): Routing asks as on the REST API, for example {"private": true} for attested hardware this gateway verified, at the model's price

### `list_tools` (~131 tokens)

List tools

Tools you can call through POST /v1/tools/{id}, paid from the same balance and key as chat, each with its price in USDF (what it costs plus 5% at most) and the input it takes, ordered by title. Every tool listed can be called now. q keeps the tools whose id, title or description has those words; a page holds up to 200, and page.next names the next one. No key needed.

Input parameters:

- `cursor` (string): page.next of the page before
- `q` (string): Words a tool's id, title or description has

### `quote_tool` (~93 tokens)

Quote a tool call

What a call to a tool would hold for this input before it runs (its most it can cost), in USDF and USD, with the tool's price. It checks the input as the call would, and runs and holds nothing. No key needed.

Input parameters:

- `input` (object): The input the call would send, as in the tool's input schema
- `tool` (string, required): Tool id from list_tools

### `x402_pay` (~291 tokens)

Pay an x402 URL

Calls a URL that asks for an x402 payment and pays it for you: the gateway pays the seller in USDC from its own float and charges this key in USDF cost plus 5% at most, no minimum (the seller's amount and a fee of at most 5% of it; never free credit), within the key's and its agent's limits. Needs an API key. Returns the seller's answer with the payment and its receipt; a payment is charged only once the chain shows it, and one that never settles costs nothing. quote: true answers what it would cost and pays nothing. Third-party tools to call this way are listed under marketplace in list_tools (GET /v1/tools?source=marketplace).

Input parameters:

- `body`: The request body: text, or JSON sent as application/json
- `headers` (object): Headers for the seller (the payment headers are the gateway's)
- `max_price` (string): The most to pay in USDF, the fee included ("0.05")
- `method` (string): Default GET, or POST when a body is given
- `network` (string): Pay on this network only: its CAIP-2 id, one GET /v1/x402/payer lists
- `quote` (boolean): Answer the price and pay nothing
- `url` (string, required): The seller's URL (https)

### `agents_market_search` (~184 tokens)

Search the agents market

Agents, APIs and tools priced per call, in one market, every listing in the same shape: its id (svc_...), name, description, tags, site and logo, how it is called (GET or POST), what one call costs in USDF from this key's balance, input and output examples, and the data policy. Ordered by popularity (default), price or newest. No key needed to search; agents_market_call calls one.

Input parameters:

- `limit` (integer)
- `max_price` (string): The most a call may cost in USDF ("0.01")
- `offset` (integer)
- `q` (string): Words to find in the name, description, tags or host
- `sort` (string): popular (default), price (cheapest first) or new
- `tag` (string): Only listings with this tag

### `agents_market_call` (~233 tokens)

Call a listing

Calls a listing of the agents market by its id (svc_..., from agents_market_search), paid from this key's USDF balance (never free credit) within the key's and its agent's limits and at most max_price: what one call costs and nothing on top; a call its seller does not answer 2xx costs nothing, or no more than what its seller kept of it. Every listing is called the same way, and answers 503 market_calls_unarmed while calls to the market are not switched on. Needs an API key. Returns the seller's answer and the receipt. The input goes to the seller, whose own policy governs what it keeps.

Input parameters:

- `id` (string, required): The listing's id (svc_...), from agents_market_search
- `input`: What the call sends: JSON for a POST listing, an object of plain values (its query) for a GET one
- `max_price` (string, required): The most this call may cost in USDF ("0.05"): required, as a seller may change its price; the listing's price is in agents_market_search

### `chat` (~717 tokens)

Chat completion

Runs a chat completion and returns the text with its receipt (tokens, price, cost, balance, settlement). With an API key it spends from that key's balance, holding the most the request can cost first. Not streamed. Output is capped at 4096 tokens. A call without a progress token answers within 55 s of arriving. With a progress token, progress is sent every 15 s and the call may run 10 minutes, so the client must reset its timeout on progress (resetTimeoutOnProgress: true in the TypeScript SDK) or wait that long. At its deadline, or when the client's connection closes, a call is cut: the text produced so far is returned with finish_reason "length" and billed on the provider's usage report where the provider gives one, otherwise on an estimate never above max_tokens; for a model whose reasoning is not streamed, at the held output budget. Cancellation messages are not supported: a call the client stops waiting for without disconnecting runs to completion or its deadline and is billed. With no key, the call is paid with x402 in USDF (signature transfer) or USDG (signed transfer), as POST /x402/v1/chat/completions: without a payment it returns isError with the payment requirements (x402Version, resource, accepts) as structuredContent; sign one accept and call again with the payment in _meta["x402/payment"], the payment argument or the PAYMENT-SIGNATURE header. The quote is the call's maximum cost at the published price (prompt at one token per byte, output at max_tokens, capped as above, no minimum), paid up front; the call is charged what it uses at that price and the rest is refunded in the asset paid, the gateway paying the gas. A paid call runs to its end or its deadline whether or not the client waits and returns the receipt and _meta["x402/payment-response"]; at the deadline the text so far is returned with finish_reason "length" and a note, charged what it used and the rest refunded. A call no provider accepted before its deadline, or whose provider failed or end…

Input parameters:

- `max_tokens` (number): Output token budget, a positive integer; defaults to the model's default_max_output, capped at max_output
- `messages` (array, required): Chat messages in the OpenAI format: objects with a role (system, user, assistant or tool) and content (text, or an array of content parts)
- `model` (string, required): Model id from list_models
- `payment`: With no key: the x402 payment for this call's quote, as the PAYMENT-SIGNATURE value (base64 JSON) or the payload object; _meta["x402/payment"] and the PAYMENT-SIGNATURE header are read too
- `temperature` (number): Sampling temperature, 0 to 2

### `balance` (~114 tokens)

Balance

With an API key: what the key can spend now, the account's balance and the amount held for requests running, and what is left of the key's budget, in USDF. With address instead, and no key: that wallet's USDF and USDG on the chain now, and how much USDF it lets the signature-transfer contract spend, which x402 payments come from.

Input parameters:

- `address` (string): A wallet address (0x...): its USDF and USDG on the chain, with no key

### `receipt` (~119 tokens)

Receipt

With the API key that made the request: its receipt, with the usage, the price sheet version, the cost and, once settled, the settlement, its transaction and the rows behind the onchain digest. With no key: the public receipt of any request id, x402 ones included, with its line in the usage log, the payment, the settlement and where its proof is (GET /x402/v1/receipts/{id}).

Input parameters:

- `request_id` (string, required): The id returned with the completion (also the x-request-id header)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/fi-usdf-gateway/api#diagnostics

## Score history

- 2026-10-22: 73
- 2026-10-21: 73
- 2026-10-20: 72
- 2026-10-19: 72
- 2026-10-18: 71
- 2026-10-17: 71
- 2026-10-16: 70

## Common questions

### What is the Foundry: prepaid AI compute in USDF MCP server?

Foundry: prepaid AI compute in USDF is an MCP server listed in the public MCP registry as fi.usdf/gateway. Prepaid AI compute in USDF: models, quotes and chat with a receipt; pay per call (x402) or by key. This page covers its hosted endpoint (https://api.usdf.fi/mcp).

### Is the Foundry: prepaid AI compute in USDF MCP server safe to use?

Foundry: prepaid AI compute in USDF scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Foundry: prepaid AI compute in USDF MCP server expose?

Foundry: prepaid AI compute in USDF exposes 10 tools: list_models, quote, list_tools, quote_tool, x402_pay, and 5 more. Their descriptions and schemas cost roughly 2,163 tokens of context every time the server is loaded.

### Does the Foundry: prepaid AI compute in USDF MCP server require authentication?

No. We connected to Foundry: prepaid AI compute in USDF without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Foundry: prepaid AI compute in USDF MCP server still maintained?

Foundry: prepaid AI compute in USDF is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.usdf.fi/mcp
- Website: https://usdf.fi/developers
- Changelog RSS feed: https://verifymcp.io/servers/fi-usdf-gateway/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/fi-usdf-gateway/api.json
- HTML version of this page: https://verifymcp.io/servers/fi-usdf-gateway/api