The first open-source MCP server for jPOS and ISO 8583. Give AI agents deterministic access to payment protocol expertise.
Server has 7 tools with explicit schemas and descriptions. Naming is verb-forward (generate_, validate_, lookup_, decode_, build_, query_). Descriptions are present and substantive (100-300 chars), exceeding the 10-char minimum. However, several tools lack parameter descriptions for all fields, and output schemas are not formally documented. Error handling is minimal, tools return dicts/strings without structured error guidance. No tool annotations (readOnlyHint, destructiveHint) despite all being read-only. Parameter validation is present but error messages are not recovery-focused.
Validate an ISO 8583 message field dictionary. Checks MTI validity, missing mandatory fields, value length violations, and potential real PANs (detected via Luhn algorithm — rejected for safety). Only test PANs (4111111111111111 etc.) are accepted.
Decode a 4-digit MTI into version, message class, function, and origin. For request messages (function digit = 0), returns the expected response MTI.
Generate a complete jPOS GenericPackager XML configuration. Parses field numbers from description, looks up correct jPOS classes, and assembles valid XML ready to save as a .xml file. Always includes fields 0 (MTI) and 1 (Bitmap).
Return server health status: version, tool count, and ChromaDB chunk count.
Return the complete ISO 8583 specification for a data element number. Returns: name, format (FIXED/LLVAR/LLLVAR), type, max_length, jpos_class_bcd, jpos_class_ascii, mandatory_for_mtis, pci_sensitive, notes. Use this before writing any GenericPackager XML.
Search the jPOS knowledge base using semantic similarity. Returns the top matching chunks with source, page, and relevance score. Expands short queries with domain terminology before embedding.
Output schemas not documented. Tools return dicts/strings without formal schema declarations. LLMs cannot reliably extract fields or plan downstream calls.
No tool annotations. All 7 tools are read-only but lack readOnlyHint in schema. Agents cannot distinguish safe tools from destructive ones.
Error handling lacks recovery guidance. validate_descriptor returns structured errors but others (generate_packager, build_message) may fail silently or with generic exceptions. No actionable error messages.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 58 | <=2025-11-25 | v2 |
Validate a jPOS Q2 deploy descriptor XML file. Checks: well-formed XML, required attributes, channel/QMUX/TM-specific rules, common property name typos.
build_message description mentions Luhn algorithm and test PANs but does not document the output schema (which fields are returned on success/failure).
query_docs accepts top_k parameter but does not document pagination or result limit enforcement. No mention of max results cap or next_cursor for large result sets.