acmt001-mcp: An MCP Server for ISO 20022 Account Management

A Model Context Protocol server that exposes the acmt001 ISO 20022 Account Management library as tools for AI agents and assistants — discover message types, inspect input schemas, validate records and financial identifiers, and generate validated XML, all from your favourite MCP client.

Latest release: v0.0.5 — six MCP tools over stdio, all backed by the shared acmt001.services layer, for Python 3.10+. See what's new →

Contents

• Overview
• Install
• Quick Start
• Tools
• Using the tools
• Benchmarks
• Development
• Licence
• Contribution
• Acknowledgements

Overview

The Model Context Protocol (MCP) is an open standard that lets AI agents and assistants discover and call external tools in a uniform way. acmt001-mcp is an MCP server that turns the acmt001 library into a set of first-class agent tools, so an assistant can generate and validate ISO 20022 acmt Account Management XML messages — the standardised instructions, confirmations, and reports that govern the lifecycle of a bank account (opening, maintenance, closing, identification, and switching) — directly from a conversation.

Every tool is a thin, typed wrapper over acmt001.services — the single shared facade also used by the CLI and REST API — so all interfaces behave identically. Tools return JSON-serialisable data; on a validation error they return an {"error": ...} payload rather than raising.

• Website: https://acmt001.com
• Source code: https://github.com/sebastienrousseau/acmt001-mcp
• Bug reports: https://github.com/sebastienrousseau/acmt001-mcp/issues

This package is part of the acmt001 suite — a set of independently installable packages that share the acmt001.services layer:

• acmt001 — the core library (CLI + REST API)
• acmt001-mcp — this package, the Model Context Protocol server
• acmt001-lsp — the Language Server Protocol server for editors

flowchart LR
    A["MCP client<br/>(Claude Desktop, IDE, agent)"] -->|stdio| B["acmt001-mcp"]
    B -->|delegates to| C["acmt001.services"]
    C -->|render + validate| D["ISO 20022 acmt XML"]

Install

acmt001-mcp runs on macOS, Linux, and Windows and requires Python 3.10+ and pip. It pulls in the core acmt001 library and the MCP SDK automatically.

python -m pip install acmt001-mcp

Note: while the core acmt001 library is not yet on PyPI, install it from source first:

python -m pip install "git+https://github.com/sebastienrousseau/acmt001.git"
python -m pip install acmt001-mcp

python -m venv venv
source venv/bin/activate        # macOS/Linux
venv\Scripts\activate           # Windows
python -m pip install -U acmt001-mcp

Quick Start

Launch the server over stdio (the FastMCP default transport):

acmt001-mcp

Register it with any MCP client (e.g. Claude Desktop) by adding it to the client's configuration:

{
  "mcpServers": {
    "acmt001": { "command": "acmt001-mcp" }
  }
}

The agent can then call the tools below to validate account data and generate ISO 20022 messages on demand.

Tools

All tools delegate to the shared acmt001.services layer, so they behave identically to the CLI and REST API.

• list_message_types — List the 34 supported acmt message types
• get_required_fields — Required input fields for a message type
• get_input_schema — Full input JSON Schema for a message type
• validate_records — Validate flat records against a message type
• validate_identifier — Validate an IBAN, BIC, or LEI
• generate_message — Generate a validated acmt XML message

Using the tools

You can invoke the tools in-process — without a transport — straight through the FastMCP instance. This mirrors what an agent receives over stdio. The runnable version of this snippet lives in examples/mcp_tools.py.

import asyncio

from acmt001_mcp.server import server

# A single flat account-opening record.
record = [
    {
        "msg_id": "ACMT-MSG-0001",
        "creation_date_time": "2026-01-15T10:30:00",
        "process_id": "ACMT-PRC-0001",
        "account_id": "GB29NWBK60161331926819",
        "account_currency": "EUR",
        "account_name": "Treasury Operating Account",
        "account_type_cd": "CACC",
        "account_servicer_bic": "NWBKGB2LXXX",
        "account_owner_name": "Acme Embedded Finance Ltd",
        "account_owner_country": "GB",
        "org_full_legal_name": "Acme Embedded Finance Limited",
        "org_country_of_operation": "GB",
        "org_id_lei": "5493001KJTIIGC8Y1R12",
    }
]


async def main() -> None:
    async def call(name, args):
        result = await server.call_tool(name, args)
        content = result[0] if isinstance(result, tuple) else result
        return content[0].text if content else ""

    # Validate an identifier.
    print(await call("validate_identifier",
                     {"kind": "lei", "value": "5493001KJTIIGC8Y1R12"}))
    # -> {"kind": "lei", "value": "5493001KJTIIGC8Y1R12", "valid": true}

    # Generate a validated ISO 20022 Account Opening Request.
    xml = await call("generate_message",
                     {"message_type": "acmt.007.001.05", "records": record})
    print(xml[:46])  # -> <?xml version="1.0" encoding="UTF-8"?> ...


asyncio.run(main())

Run it directly:

python examples/mcp_tools.py

Benchmarks

python benches/bench_tool_dispatch.py           # full run
python benches/bench_tool_dispatch.py --quick   # what CI runs

The benchmark measures what an agent waits for: the dispatch floor (list_message_types, around a microsecond), the metadata lookups used to build a request, and the two batch tools side by side.

The result worth knowing is the asymmetry between those two. validate_records checks every record, so it is linear in batch size. generate_message, for a single-account message type like the default acmt.007.001.05, renders only the first record — twenty-seven of the thirty-four templates work this way. So validating a hundred records and generating from them costs roughly 260 ms of validation against 6 ms of generation, and returns one message rather than a hundred.

That is correct ISO 20022 behaviour and a real trap when batching, which is why the benchmark prints output size beside the timings: flat bytes across growing input is what tells you the rest of the batch was not rendered. See docs/benchmarks.md.

Development

acmt001-mcp uses Poetry and mise.

git clone https://github.com/sebastienrousseau/acmt001-mcp.git && cd acmt001-mcp
mise install
poetry install
poetry shell

This package depends on the core acmt001 library. Until it is on PyPI, install it from source first: pip install "git+https://github.com/sebastienrousseau/acmt001.git".

A Makefile orchestrates the quality gates (kept in lockstep with CI):

make check        # all gates (REQUIRED before commit)
make test         # pytest
make lint         # ruff + black
make type-check   # mypy --strict

Related MCP Servers

Part of the ISO 20022 MCP Suite — open-source, Apache-2.0 licensed MCP servers for banking and financial-services AI agents:

MCP Registry

mcp-name: io.github.sebastienrousseau/acmt001-mcp

Licence

Licensed under the Apache Licence, Version 2.0. Any contribution submitted for inclusion shall be licensed as above, without additional terms.

Contribution

Contributions are welcome — see the contributing instructions. Thanks to all contributors.

Acknowledgements

Built on the acmt001 ISO 20022 Account Management library and the Model Context Protocol Python SDK.