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
Available components
Last scanned (2 hours ago)
Scores higher than 55% of npm servers
Category Finance and Payments
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. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- Dependency health was assessed across the 140 of 146 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 75 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability69
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1377 tokens (~114/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage87
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 61% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 2 Nov 26 +1
- Stability: 0.97 → pass security
- 1 Nov 26 −1
- Stability: pass → 0.97 functional
- 27 Oct 26 0
- CVE-2026-114142 affects this package: high ▼ security
- Package version: 0.1.6 → 0.1.9 functional
- 26 Oct 26 +1
- Stability: 0.97 → pass security
- 25 Oct 26 −1
- Stability: pass → 0.97 functional
- 24 Oct 26 −2
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. security
- 23 Oct 26 0
- CVE-2026-114144 affects this package: high ▼ security
- CVE-2026-114143 affects this package: high ▼ security
- CVE-2026-114141 affects this package: high ▼ security
- 21 Oct 26 0
- Package version: 0.1.6 → 0.1.9 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/@ramp-kit/mcp@0.1.9
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 7 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-4qx8-w7c3-pj3p | CVE-2026-114141 | high | yes | |
| GHSA-82x6-q7mm-w9cf | CVE-2026-77465 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-9j65-hcg3-gc64 | CVE-2026-114143 | high | yes | |
| GHSA-9qmh-m7c6-f92p | CVE-2026-114144 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-h895-cgqg-jf52 | CVE-2026-114142 | high | yes | |
| GHSA-v5mp-jgw5-2x6j | CVE-2026-63376 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:L | yes |
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 140 packages
| Packages resolved | 140 |
|---|---|
| Deprecated | 1 |
| Stale | 47 |
| Tree resolution | Partial |
The dependency tree was only partially resolved, so these counts may be incomplete.
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_manteca_user ~90
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.
| Name | Type | Req | Description |
|---|---|---|---|
| userAnyId | string | yes | Id, numberId or externalId to validate |
No output schema declared.
No examples provided.
compare_quotes ~125
Fan the same quote request out to every eligible provider and compare live rates (multi-anchor comparison).
| Name | Type | Req | Description |
|---|---|---|---|
| assetIdentifier | string | yes | – |
| direction | string | yes | – |
| fiatCurrency | string | yes | – |
| network | string | – | – |
| payoutBankAccount | string | – | Offramp shorthand: fiat payout bank account (CBU/CLABE/IBAN/PIX key) |
| payoutDestination | object | – | Offramp payout destination with provider-specific extras; overrides payoutBankAccount |
| sourceAmount | string | yes | – |
| walletAddress | string | – | – |
No output schema declared.
No examples provided.
create_order ~107
Turn a live quote (from get_quote/compare_quotes) into an order. Returns the normalized order with deposit instructions (PIX charge or SPEI CLABE). Manteca offramps require payoutBankAccount to have been passed at quote time. Sandbox/mock only through this server unless RAMPKIT_ENV=production.
| Name | Type | Req | Description |
|---|---|---|---|
| bankAccountId | string | – | Etherfuse fiat-leg bank account (defaults to first compliant) |
| quoteId | string | yes | Quote id returned by get_quote |
No output schema declared.
No examples provided.
diagnose_onboarding ~90
Full 'why is this user stuck in ONBOARDING?' diagnosis for a Manteca user: the missing per-country KYC FIELDS plus the onboarding TASK map (e.g. IDENTITY_VALIDATION = ID images pending — a user with zero missing fields can still be blocked by a task; Argentina always requires images). Requires MANTECA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| userAnyId | string | yes | – |
No output schema declared.
No examples provided.
get_documentation ~110
LATAM Ramp Kit documentation. Topics: overview (what it is and solves), quickstart (code to integrate), sandbox-setup (Etherfuse/Manteca test credentials), environments (testnet/mainnet step-by-step + where credentials go: backend proxy vs frontend env vars vs no-backend SEP route), architecture (lifecycle, provider mapping, Stellar specifics), production (path to mainnet), troubleshooting (verified error fixes). Start here.
| Name | Type | Req | Description |
|---|---|---|---|
| topic | string | yes | Documentation topic to read |
No output schema declared.
No examples provided.
get_order ~46
Fetch the current normalized state of an order (created → awaiting_deposit → processing → settled | failed | cancelled).
| Name | Type | Req | Description |
|---|---|---|---|
| orderId | string | yes | – |
| provider | string | – | – |
No output schema declared.
No examples provided.
get_quote ~220
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.
| Name | Type | Req | Description |
|---|---|---|---|
| assetIdentifier | string | yes | From list_assets |
| direction | string | yes | – |
| fiatCurrency | string | yes | e.g. BRL, MXN |
| network | string | – | Default stellar |
| payoutBankAccount | string | – | Offramp shorthand: the user's fiat payout bank account in local format (CBU, CLABE, IBAN, PIX key…). Required for Manteca offramps. For countries needing extra fields (bankCode, accountType…), use pa… |
| payoutDestination | object | – | Offramp payout destination with provider-specific extras (bankCode, accountType, network…), passed through as-is. Overrides payoutBankAccount. |
| provider | string | – | – |
| sourceAmount | string | yes | Decimal string, fiat for onramp |
| walletAddress | string | – | Destination Stellar address |
No output schema declared.
No examples provided.
get_wallet_state ~77
Inspect a Stellar wallet: does the account exist, XLM balance, asset balances, and claimable balances waiting to be claimed (sponsored onramp deliveries).
| Name | Type | Req | Description |
|---|---|---|---|
| assetIdentifier | string | – | Optional "CODE:ISSUER" to check a specific trustline |
| publicKey | string | yes | Stellar public key (G…) |
No output schema declared.
No examples provided.
list_assets ~75
List tradable assets for a provider on a network. Asset identifiers are environment-specific — always use these, never hardcode.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | Fiat currency hint, e.g. brl |
| network | string | – | Network, default stellar |
| provider | string | – | Provider name or "auto" (default) |
No output schema declared.
No examples provided.
list_providers ~36
List configured ramp providers with their capabilities (countries, fiat currencies, settlement networks, Stellar-native flag) and whether live credentials are present.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
onboard_manteca_user ~276
Create (onboard) a Manteca user — the mandatory prerequisite for any Manteca quote/order. The exchange fixes the user's ONE settlement currency (e.g. BRAZIL → BRL); to pay out in several countries, onboard one user per country. Sandbox onboarding auto-completes to ACTIVE in seconds (the sandbox dashboard has no onboarding UI — this API is the only path). CAVEATS: if the person already exists, Manteca returns 200 with the EXISTING user and a causedConflict flag — use the returned ids, not your externalId; Brazil validates legalId against a real-person registry (use the docs' test CPF 403.608.938-21); Argentina always requires ID images (diagnose_onboarding shows the task). Requires MANTECA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | – | |
| exchange | string | yes | Country exchange, e.g. BRAZIL, ARGENTINA, COLOMBIA |
| externalId | string | yes | Your stable id for this user |
| legalId | string | yes | Local legal id: CPF (BR), DNI (AR), CURP/RFC (MX)… |
| personalData | object | – | Per-country KYC fields (sex, phoneNumber, address.street…); diagnose_onboarding reports what's missing |
No output schema declared.
No examples provided.
simulate_deposit ~125
SANDBOX ONLY: simulate the incoming fiat transfer for an order, as if the user paid. Refuses to run in production. Works for Etherfuse, Mock and Manteca (Manteca: instant rails PIX/BRL and SPEI/MXN settle sandbox onramps WITHOUT simulation — use this for bank-transfer rails like CLP; needs MANTECA_LEGAL_ENTITY env; BANK_ACCOUNT_NF means the (legalEntity, currency) pair has no provisioned sandbox account).
| Name | Type | Req | Description |
|---|---|---|---|
| orderId | string | yes | – |
| provider | string | – | – |
No output schema declared.
No examples provided.
How do I install the io.github.armandocodecr/ramp-kit MCP server?
io.github.armandocodecr/ramp-kit runs locally as an npm package, launched with npx -y @ramp-kit/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @ramp-kit/mcp
claude mcp add armandocodecr-ramp-kit -- npx -y @ramp-kit/mcp
What is the io.github.armandocodecr/ramp-kit MCP server?
io.github.armandocodecr/ramp-kit is an MCP server listed in the public MCP registry as io.github.armandocodecr/ramp-kit. LATAM fiat ramps on Stellar for AI agents: live quotes, sandbox orders, PIX/SPEI simulation, docs. This page covers its npm package (@ramp-kit/mcp).
Is the io.github.armandocodecr/ramp-kit MCP server safe to use?
io.github.armandocodecr/ramp-kit scores 77 out of 100 on VerifyMCP. We recorded 7 known advisories against it as of 5 November 2026. It declares no install or post-install scripts. 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 io.github.armandocodecr/ramp-kit MCP server expose?
io.github.armandocodecr/ramp-kit exposes 12 tools: get_documentation, list_providers, list_assets, get_quote, compare_quotes, and 7 more. Their descriptions and schemas cost roughly 1,377 tokens of context every time the server is loaded.
Is the io.github.armandocodecr/ramp-kit MCP server still maintained?
io.github.armandocodecr/ramp-kit is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.armandocodecr/ramp-kit MCP server under?
io.github.armandocodecr/ramp-kit declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.