# io.github.armandocodecr/ramp-kit (npm · @ramp-kit/mcp)

LATAM fiat ramps on Stellar for AI agents: live quotes, sandbox orders, PIX/SPEI simulation, docs

- Trust score: 73/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-16

## Components

- npm · `@ramp-kit/mcp`: 73/100 (this document), [markdown](https://verifymcp.io/servers/armandocodecr-ramp-kit/ramp-kit-mcp.md), [page](https://verifymcp.io/servers/armandocodecr-ramp-kit/ramp-kit-mcp)

## Channel facts

- Registry: `npm`
- Package: `@ramp-kit/mcp`
- Version: `0.1.6`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-16.

- **Supply Chain Security**: 97/100
  - No malware found by supply-chain analysis.
  - Known CVEs were checked across the 143 of 149 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Dependency health was assessed across the 143 of 149 dependencies we could resolve, so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 9 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 750 tokens (~75/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 54% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add armandocodecr-ramp-kit -- npx -y @ramp-kit/mcp
```

### Codex

```bash
codex mcp add armandocodecr-ramp-kit -- npx -y @ramp-kit/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "armandocodecr-ramp-kit": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@ramp-kit/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add armandocodecr-ramp-kit --command npx --arg -y --arg @ramp-kit/mcp
```

### Hermes

```yaml
mcp_servers:
  armandocodecr-ramp-kit:
    command: "npx"
    args: ["-y", "@ramp-kit/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "armandocodecr-ramp-kit": {
      "command": "npx",
      "args": [
        "-y",
        "@ramp-kit/mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-16 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-14 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-12 (score 71, +1)

- [functional regression] Security disclosure: unverified → fail

### 2026-08-11 (score 70, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-10 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-08 (score 69, +34)

- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.13
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 54

### 2026-08-06 (score 35, +12)

- [security improvement] Known CVEs: unverified → partial
- [security improvement] Source repository: fail → pass
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.07
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 54
- [functional] Package version: 0.1.5 → 0.1.6

### 2026-08-05 (score 23, −12)

- [security regression] Known CVEs: partial → unverified
- [security regression] Source repository: pass → fail
- [functional regression] Dependency health: partial → unverified
- [functional] Package version: 0.1.1 → 0.1.5
- [functional] Package version: 0.1.1 → 0.1.3
- [functional] Package version: 0.1.1 → 0.1.2

## MCP tools (10)

### `get_documentation` (~83 tokens)

LATAM Ramp Kit documentation. Topics: overview (what it is and solves), quickstart (code to integrate), sandbox-setup (Etherfuse/Manteca test credentials), architecture (lifecycle, provider mapping, Stellar specifics), production (path to mainnet), troubleshooting (verified error fixes). Start here.

Input parameters:

- `topic` (string, required): Documentation topic to read

### `list_providers` (~36 tokens)

List configured ramp providers with their capabilities (countries, fiat currencies, settlement networks, Stellar-native flag) and whether live credentials are present.

### `list_assets` (~75 tokens)

List tradable assets for a provider on a network. Asset identifiers are environment-specific — always use these, never hardcode.

Input parameters:

- `currency` (string): Fiat currency hint, e.g. brl
- `network` (string): Network, default stellar
- `provider` (string): Provider name or "auto" (default)

### `get_quote` (~124 tokens)

Get a live ramp quote (fiat→crypto or crypto→fiat). Returns target amount, rate, fees and expiry. The quote id can be passed to create_order before it expires.

Input parameters:

- `assetIdentifier` (string, required): From list_assets
- `direction` (string, required)
- `fiatCurrency` (string, required): e.g. BRL, MXN
- `network` (string): Default stellar
- `provider` (string)
- `sourceAmount` (string, required): Decimal string, fiat for onramp
- `walletAddress` (string): Destination Stellar address

### `compare_quotes` (~73 tokens)

Fan the same quote request out to every eligible provider and compare live rates (multi-anchor comparison).

Input parameters:

- `assetIdentifier` (string, required)
- `direction` (string, required)
- `fiatCurrency` (string, required)
- `network` (string)
- `sourceAmount` (string, required)
- `walletAddress` (string)

### `create_order` (~89 tokens)

Turn a live quote (from get_quote/compare_quotes) into an order. Returns the normalized order with deposit instructions (PIX charge or SPEI CLABE). Sandbox/mock only through this server unless RAMPKIT_ENV=production.

Input parameters:

- `bankAccountId` (string): Etherfuse fiat-leg bank account (defaults to first compliant)
- `quoteId` (string, required): Quote id returned by get_quote

### `get_order` (~46 tokens)

Fetch the current normalized state of an order (created → awaiting_deposit → processing → settled | failed | cancelled).

Input parameters:

- `orderId` (string, required)
- `provider` (string)

### `simulate_deposit` (~57 tokens)

SANDBOX ONLY: simulate the incoming fiat transfer (PIX/SPEI) for an order, as if the user paid. Refuses to run in production.

Input parameters:

- `orderId` (string, required)
- `provider` (string)

### `check_manteca_user` (~90 tokens)

Validate a Manteca userAnyId (internal id, numberId or externalId) and report onboarding status. Use when quotes fail with USER_NF / 'User not found' — the id must belong to an onboarded user of YOUR Manteca account. Requires MANTECA_API_KEY.

Input parameters:

- `userAnyId` (string, required): Id, numberId or externalId to validate

### `get_wallet_state` (~77 tokens)

Inspect a Stellar wallet: does the account exist, XLM balance, asset balances, and claimable balances waiting to be claimed (sponsored onramp deliveries).

Input parameters:

- `assetIdentifier` (string): Optional "CODE:ISSUER" to check a specific trustline
- `publicKey` (string, required): Stellar public key (G…)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/armandocodecr-ramp-kit/ramp-kit-mcp#diagnostics

## Score history

- 2026-08-16: 73
- 2026-08-15: 72
- 2026-08-14: 72
- 2026-08-13: 71
- 2026-08-12: 71
- 2026-08-11: 70
- 2026-08-10: 70
- 2026-08-09: 69
- 2026-08-08: 69
- 2026-08-07: 35
- 2026-08-06: 35
- 2026-08-05: 23
- 2026-08-04: 35

## Links

- npm package: https://www.npmjs.com/package/@ramp-kit/mcp
- Socket report: https://socket.dev/npm/package/@ramp-kit/mcp
- Repository: https://github.com/armandocodecr/latam-ramp-kit
- Changelog RSS feed: https://verifymcp.io/servers/armandocodecr-ramp-kit/ramp-kit-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/armandocodecr-ramp-kit/ramp-kit-mcp.json
- HTML version of this page: https://verifymcp.io/servers/armandocodecr-ramp-kit/ramp-kit-mcp