ISO 20022 Navigator

ISO 20022 legacy and scheme mappings

iso20022_legacy_and_scheme_mappings

Read-onlyIdempotent

Use for ANY question about what replaces or corresponds to a legacy payment message (SWIFT MT such as MT103, MT202, MT940; NACHA; CHAPS), or which payment schemes use an ISO 20022 message (pacs.008, pain.001, pain.008, camt.053; SEPA, NPP, CHAPS, Lynx, CIPS and others). Call it even when the answer seems well known: it returns sourced, current mappings with status and caveats.

For "which schemes use X", call once with only the message: the response lists every recorded scheme (without descriptions, to keep it compact). Omit standard unless the user names one scheme; with standard, the response includes that scheme's description.

Legacy input (MT103, 940, ACH Statement): returns its ISO 20022 equivalent(s) in legacy_equivalents.
ISO 20022 input (pacs.008): returns legacy_equivalents (legacy messages that map to it) and used_by_schemes (schemes that use it).

Mappings are message-level only; this tool does not map individual fields and has no information about a message's structure, elements or rules. Do not cite it for those. ISO 20022 messages that have been retired are returned flagged with iso20022_deactivated_in, not hidden.

Input Schema

Name	Required	Description	Default
`message`	Yes	A legacy message (e.g. 'MT103', 'MT 202COV', '940', 'ACH Statement') or an ISO 20022 message (e.g. 'pacs.008', 'camt.053.001.08').
`standard`	No	Omit (or leave empty) unless the user names one specific standard or scheme. Omitted returns every recorded scheme and legacy equivalent in one call; do not use this to check schemes one by one. Examples when the user names one: 'SWIFT_MT', 'SEPA', 'NPP', 'CHAPS'.

Output Schema

Name	Required	Description
`found`	Yes
`input`	Yes	The message identifier as interpreted by the server
`notes`	No	Caveats to pass on to the user
`input_kind`	Yes
`provenance`	Yes
`used_by_schemes`	No	Payment schemes that use this ISO 20022 message
`legacy_equivalents`	No	Legacy or non-ISO messages (SWIFT MT, NACHA, CHAPS legacy) and their ISO 20022 equivalent
`iso20022_message_name`	No	Name of the ISO 20022 message, when the input is one
`iso20022_deactivated_in`	No	Navigator data load (quarter) in which the input message was marked deactivated; absent if current

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 7, 2026

addedOutput schema / $defs / Provenance / description

Added value: +"Where the data comes from [3.6]. Each tool supplies its own `scope`."

removedOutput schema / $defs / Provenance / properties / scope / default

Removed value: -"Message-level mappings only (not field-level). ISO 20022 messages at their latest version only."

addedOutput schema / $defs / Provenance / required
```
Added value: +[
+  "scope"
+]
```

changedOutput schema / required

Previous value: -[
-  "found",
-  "input",
-  "input_kind"
-]New value: +[
+  "found",
+  "input",
+  "input_kind",
+  "provenance"
+]

First observedOct 6, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent/non-destructive annotations it discloses real behavioral traits: results are sourced with status and caveats, 'schemes' responses omit descriptions for compactness while `standard` adds a scheme description, and retired ISO messages are returned flagged via iso20022_deactivated_in rather than hidden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The imperative 'Use for ANY question...' is front-loaded and the bulleted legacy/ISO cases are easy to scan. It is somewhat long and repeats the omit-`standard` guidance already present in the schema, keeping it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, yet the description still previews the return structure (legacy_equivalents, used_by_schemes, iso20022_deactivated_in), so an agent fully understands inputs and outputs. Nothing material is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the `standard` description already states the omit-by-default rule, so baseline is 3. The description goes further by explaining the differentiated response shape for legacy vs ISO input and the effect of `standard` on output size, adding genuine meaning. It stops just short of syntax details, so a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: mapping legacy payment messages (MT103, NACHA, CHAPS) to/from ISO 20022 messages and identifying which schemes use a message. It explicitly bounds the scope ('message-level only') and disclaims field-level mapping, which cleanly separates it from any sibling focused on transaction codes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance ('Use for ANY question about...', 'Call it even when the answer seems well known'), the exact condition for including the optional `standard` param ('Omit unless the user names one scheme'), and an explicit when-not ('this tool does not map individual fields... Do not cite it for those').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All ISO 20022 Navigator tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.