ebcdicjp-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Japanese mainframe data: start with describe_layout on the copybook, then read_records with a small limit. If kana or lowercase look wrong, try detect_codepage. Report the issues read_records returns instead of guessing what the bytes meant.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| describe_layoutB | Parse a COBOL copybook and list every field with its byte position, length and type (text = PIC X with SO/SI kanji, dbcs = PIC N, zoned, packed = COMP-3, binary = COMP). |
| read_recordsA | Decode records of a Japanese mainframe data file (fixed-length, or variable with RDW) using a copybook. Returns nested JSON per record plus issues located by field path and byte offset (pos is 1-based): unmapped bytes, 外字 (gaiji, shown as 〓), broken SO/SI, invalid packed/zoned numbers. Code page and RDW are detected unless given; read the notes. Read a few records first (limit). |
| write_recordsA | Build a fixed-length EBCDIC file (test data) from JSON records shaped like read_records output. Missing fields are spaces / zero. Reports characters that will not read back the same (〜 → ~). |
| decode_bytesB | Decode hex bytes (e.g. from a hex dump or an error message) as Japanese EBCDIC, with problems listed. |
| encode_textB | Encode text to Japanese EBCDIC hex (SO/SI added around kanji). Lists unencodable and one-way characters. |
| detect_codepageA | Guess whether a data file is IBM930 or IBM939 (says 'ambiguous' with both previews when it can't tell). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct primary action: copybook introspection, hex decoding, file reading, file writing, text encoding, and codepage detection. There is mild overlap between decode_bytes and read_records (both decode EBCDIC bytes) and between encode_text and write_records (both encode to EBCDIC), but descriptions make the intended scope clear.
All six tools use a consistent snake_case verb_noun pattern: describe_layout, decode_bytes, read_records, write_records, encode_text, detect_codepage. No mixed conventions or ambiguous abbreviations.
Six tools is well-scoped for a specialized Japanese EBCDIC/copybook utility server. Each tool covers a distinct part of the workflow without obvious redundancy or missing bulk operations.
The surface covers copybook parsing, record reading/writing, hex decoding, text encoding, and codepage detection, which are the core operations for this domain. A dedicated decode_text operation or copybook validation tool would improve symmetry, but the existing tools allow agents to complete the main workflows.