# Payment Intelligence (npm · payment-intelligence-mcp)

Offline ISO 20022 payment tools: explain and scrub pacs/camt, CBPR+, SSI checks, IBAN and BIC.

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `payment-intelligence-mcp`: 74/100 (this document), [markdown](https://verifymcp.io/servers/raafet57-payment-intelligence/payment-intelligence-mcp.md), [page](https://verifymcp.io/servers/raafet57-payment-intelligence/payment-intelligence-mcp)

## Channel facts

- Registry: `npm`
- Package: `payment-intelligence-mcp`
- Version: `0.3.2`
- 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 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **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 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2282 tokens (~207/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 97% 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.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Payment Intelligence MCP server?

Payment Intelligence runs locally as an npm package, launched with npx -y payment-intelligence-mcp. 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 raafet57-payment-intelligence -- npx -y payment-intelligence-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "raafet57-payment-intelligence": {
      "command": "npx",
      "args": [
        "-y",
        "payment-intelligence-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "raafet57-payment-intelligence": {
      "command": "npx",
      "args": [
        "-y",
        "payment-intelligence-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add raafet57-payment-intelligence -- npx -y payment-intelligence-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "raafet57-payment-intelligence": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "payment-intelligence-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add raafet57-payment-intelligence --command npx --arg -y --arg payment-intelligence-mcp
```

### Hermes

```yaml
mcp_servers:
  raafet57-payment-intelligence:
    command: "npx"
    args: ["-y", "payment-intelligence-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "raafet57-payment-intelligence": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "payment-intelligence-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add raafet57-payment-intelligence -t stdio -c npx -a -y payment-intelligence-mcp
```

### Other

```json
{
  "mcpServers": {
    "raafet57-payment-intelligence": {
      "command": "npx",
      "args": [
        "-y",
        "payment-intelligence-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.

### 2026-11-04 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (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.

### 2026-10-31 (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.

### 2026-10-29 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (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.

### 2026-10-25 (score 69, +1)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.10 → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.3.1 → 0.3.2

### 2026-10-23 (score 68, +12)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → pass

### 2026-10-22 (score 56, +13)

- [security regression] Tool safety: pass → unverified
- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Schema quality: 124 → 204
- [functional regression] Schema quality: 124 → 193
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Dependency health: unverified → pass
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.1.1 → 0.3.1
- [functional] Package version: 0.1.1 → 0.3.0

## MCP tools (11)

### `validate_iban` (~59 tokens)

Validate IBAN

Validate an IBAN offline against the bundled SWIFT IBAN Registry snapshot: country, length, BBAN structure and MOD-97 check digits. Does not confirm the account exists.

Input parameters:

- `iban` (string, required): IBAN, with or without spaces.

### `build_iban` (~97 tokens)

Build IBAN

Build an IBAN from its BBAN fields and compute the MOD-97 check digits. Call without `fields` first to get the country's field template.

Input parameters:

- `country_code` (string, required): ISO 3166 alpha-2 country code, e.g. DE.
- `fields` (object): Map of template field id to value, e.g. { bank: '37040044', account: '0532013000' }.

### `check_bic` (~214 tokens)

Check BIC syntax

ISO 9362 BIC syntax and ISO 3166 country-code checks. No bank directory is bundled. With `reference_path` (or the PAYMENT_INTELLIGENCE_REFERENCE_PATH setting), also looks the BIC up in the user's own BIC Directory, Payments Directory, BIC Plus or other provider export: name, location, current or expired, successor BIC, and service participation. A directory record does not prove reachability for a specific payment; never use it alone for routing or compliance decisions.

Input parameters:

- `as_of` (string): Date for current or expired, YYYY-MM-DD. Defaults to today.
- `bic` (string, required): 8- or 11-character BIC.
- `reference_path` (string): Optional: the user's reference data, read locally. An unzipped SWIFTRef BIC Directory or Payments Directory folder, one of its files, a legacy SWIFTRef product file (BIC Plus, Bank Directory Plus, ..…

### `lookup_reference_data` (~343 tokens)

Look up identifiers in your reference data

Look up BICs (BIC8 or BIC11), national clearing codes (sort codes, ABA, IFSC, CNAPS, ...) and LEIs in the user's own reference files, read locally: SWIFTRef BIC Directory and Payments Directory folders (IDENTIFIERS, including historical, PARTICIPANTS and RELATIONSHIPS files; layouts come from the STRUCTURES file), legacy SWIFTRef products (BIC Plus, BIC Directory 2018, Bank Directory Plus, IBAN Plus, SEPA routing, Reach Plus, gpi), or a CSV/TSV export from any provider or in-house system. Returns per identifier: directory records (name, town, country, current or expired, successor), national IDs linked to a BIC, service participation, and SSI relationship counts with masked accounts. Only matching records are returned. No reference data ships with the plugin.

Input parameters:

- `as_of` (string): Date for current or expired, YYYY-MM-DD. Defaults to today.
- `column_map` (object): For a CSV/TSV whose headers are not recognised: map fields to header names, for example {"id": "Swift Code", "name": "Bank"}. Fields: id, idType, name, town, country, status, modification, start, sto…
- `ids` (array, required): Identifiers to look up, up to 50 per call.
- `path` (string): The reference data: a folder (for example an unzipped SWIFTRef download) or one file. Defaults to the PAYMENT_INTELLIGENCE_REFERENCE_PATH setting.

### `explain_payment_message` (~269 tokens)

Explain payment message

Explain an ISO 20022 payment message. pacs.008, pacs.009 and camt.053 get a plain-language narrative; pacs.002, pacs.004, camt.052 and camt.054 get a structured field projection. Case messages (camt.056 cancellation request, camt.029 resolution, camt.110 investigation request, camt.111 investigation response, the older camt.026, camt.027, camt.028 and camt.087, and the Swift Tracker messages trck.003 alert and trck.005 case status) get the projection plus a `case` field: case id, investigation type, status, reason, the underlying payment's UETR and references, camt.111 answer details (booking confirmation, payment status, amendments, compensation, value date adjustment) and any MT 199 copy Swift embedded in a delivered camt.110, with what it leaves out. All get an operator summary and quick insights. Field projection for triage, not usage-guideline rule validation.

Input parameters:

- `path` (string): Path to a local XML file. Prefer this for real data so it never enters the chat.
- `xml` (string): The ISO 20022 XML message, inline.

### `scrub_payment_message` (~148 tokens)

Scrub payment message

Replace names, IBANs, account ids, UETRs and references in a pacs/camt message with consistent pseudonyms. With `path` + `output_path`, writes the scrubbed copy to disk and returns only masked statistics, so the original data never enters the conversation. Never overwrites an existing file.

Input parameters:

- `options` (object)
- `output_path` (string): Where to write the scrubbed XML. Must not exist yet and must differ from `path`.
- `path` (string): Path to a local XML file. Prefer this for real data so it never enters the chat.
- `xml` (string): The ISO 20022 XML message, inline.

### `check_cbpr_readiness` (~89 tokens)

Check CBPR+ readiness

Local CBPR+ readiness hints: AppHdr/Document namespaces, schema-profile coverage, UETR, BIC and IBAN syntax. Readiness hints, not usage-rule validation.

Input parameters:

- `path` (string): Path to a local XML file. Prefer this for real data so it never enters the chat.
- `xml` (string): The ISO 20022 XML message, inline.

### `analyze_payment_lifecycle` (~160 tokens)

Analyze payment lifecycle

Group a set of ACK/NACK, pacs and camt files by shared identifiers (UETR, EndToEndId, TxId) into threads with a timeline and warnings. Case messages (camt.026, camt.027, camt.028, camt.029, camt.056, camt.087, camt.110, camt.111) and Tracker messages (trck.003, trck.005) join the thread of the payment they quote; a camt.111 or trck.005 joins its camt.110 by EIR. Works only on the files given.

Input parameters:

- `documents` (array): Inline documents.
- `paths` (array): Local file paths.

### `validate_ssi_file` (~338 tokens)

Validate SSI file

Validate a standing settlement instruction (SSI) file: a SWIFTRef SSI Plus V3 extract or a CSV/TSV export. Checks BIC, ISO country, ISO 4217 currency and SSI asset-category formats, required fields, preferred flags, lifecycle dates, staleness, and conflicts (two preferred correspondents, overlapping active instructions). Rule ids match SSI Control Tower. Accounts are masked in the output.

Input parameters:

- `as_of` (string): Date to judge active and stale instructions, YYYY-MM-DD. Defaults to today.
- `column_map` (object): For an export whose headers are not recognised (any provider, for example LexisNexis or an in-house system): map SSI fields to header names, for example {"ownerBic": "Bank SWIFT", "accountHolderBic":…
- `max_findings` (integer): Maximum findings to list (default 50, max 500).
- `ssi_content` (string): The SSI file content, inline (small files only).
- `ssi_path` (string): Path to the local SSI file: SWIFTRef SSI Plus, a SWIFTRef Payments Directory RELATIONSHIPS file, or a CSV/TSV from any provider. Prefer this: the file never enters the chat.

### `check_payment_against_ssi` (~513 tokens)

Check payment against SSI file

Check that a payment pays the beneficiary institution through the correspondent and account in the user's own SSI file. Reads the route from a pacs.008 (creditor agent, last intermediary, CdtrAgtAcct) or pacs.009 (creditor, creditor agent, CdtrAcct), or from explicit fields, then looks up owner BIC + currency + asset category and compares with the preferred SSI effective on the value date. Returns MATCH, ACCOUNT_MISMATCH, AGENT_MISMATCH, NOT_PREFERRED, AMBIGUOUS_SSI, NO_EFFECTIVE_SSI or NO_SSI per transaction. Accounts are masked.

Input parameters:

- `account` (string): Account at the correspondent used by the payment. Overrides the message.
- `account_holder_bic` (string): Correspondent (account-holding institution) BIC used by the payment. Overrides the message.
- `asset_category` (string): SSI asset category such as COPA, CASH, FOEX, SECU. Overrides the default for the message type.
- `column_map` (object): For an export whose headers are not recognised (any provider, for example LexisNexis or an in-house system): map SSI fields to header names, for example {"ownerBic": "Bank SWIFT", "accountHolderBic":…
- `currency` (string): ISO 4217 currency. Overrides the message.
- `owner_bic` (string): Beneficiary institution BIC (the SSI owner). Overrides the message.
- `path` (string): Path to a local XML file. Prefer this for real data so it never enters the chat.
- `ssi_content` (string): The SSI file content, inline (small files only).
- `ssi_path` (string): Path to the user's SSI file: SWIFTRef SSI Plus V3, a SWIFTRef Payments Directory RELATIONSHIPS file, or a CSV/TSV from any provider.
- `value_date` (string): Value date, YYYY-MM-DD. Defaults to the message settlement date, else today.
- `xml` (string): The ISO 20022 XML message, inline.

### `decode_reason_code` (~52 tokens)

Decode status or reason code

Explain an ISO 20022 status or reason code such as RJCT, AC01 or MD07. Omit `code` to list the curated set.

Input parameters:

- `code` (string): Status or reason code.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/raafet57-payment-intelligence/payment-intelligence-mcp#diagnostics

## Score history

- 2026-11-05: 74
- 2026-11-04: 74
- 2026-11-03: 73
- 2026-11-02: 73
- 2026-11-01: 72
- 2026-10-31: 72
- 2026-10-30: 71
- 2026-10-29: 71
- 2026-10-28: 70
- 2026-10-27: 70
- 2026-10-26: 69
- 2026-10-25: 69
- 2026-10-24: 68
- 2026-10-23: 68
- 2026-10-22: 56
- 2026-10-21: 43

## Common questions

### What is the Payment Intelligence MCP server?

Payment Intelligence is an MCP server listed in the public MCP registry as io.github.Raafet57/payment-intelligence. Offline ISO 20022 payment tools: explain and scrub pacs/camt, CBPR+, SSI checks, IBAN and BIC. This page covers its npm package (payment-intelligence-mcp).

### Is the Payment Intelligence MCP server safe to use?

Payment Intelligence scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting 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 Payment Intelligence MCP server expose?

Payment Intelligence exposes 11 tools: validate_iban, build_iban, check_bic, lookup_reference_data, explain_payment_message, and 6 more. Their descriptions and schemas cost roughly 2,282 tokens of context every time the server is loaded.

### Is the Payment Intelligence MCP server still maintained?

Payment Intelligence 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 Payment Intelligence MCP server under?

Payment Intelligence declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/payment-intelligence-mcp
- Socket report: https://socket.dev/npm/package/payment-intelligence-mcp
- Repository: https://github.com/Raafet57/payment-intelligence-plugin
- Changelog RSS feed: https://verifymcp.io/servers/raafet57-payment-intelligence/payment-intelligence-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/raafet57-payment-intelligence/payment-intelligence-mcp.json
- HTML version of this page: https://verifymcp.io/servers/raafet57-payment-intelligence/payment-intelligence-mcp