sdc-mapper-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | URL of the SDCStudio host from which published models are fetched (corresponds to the --host option). | |
| LOG_DIR | No | Directory for the hash-chained log (corresponds to the --log-dir option). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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 |
|---|---|
| list_targetsA | The target mappers installed: each target format and version, its package, and how it writes each ISO 21090 Exceptional Value (preserved, degraded, carried or lost). |
| map_recordA | Map one Governed Data Record to one target format. The record is validated first: valid, valid with Exceptional Values (one bad value is marked, not fatal), or refused with the reasons. Returns the output (inline, or written to output_dir), the coverage report (how every value reached the target, and what happened to every Exceptional Value), one sentence of what the target could not say, and the hash of the log entry. The model is the one the record names unless ct_id or directory is given. |
| check_mappingB | Validate a mapping file against the mapping schema, and, given a model, check it is bound to that model's current schema. |
| fidelityB | Run every installed mapper on one record and compare what each target did with each Exceptional Value: one row per Exceptional Value, one column per target. Shows which formats can say why a value is missing or unusable, and which can only leave it empty. |
| log_summaryB | Read the log back over a window: calls, outcomes, value classes and Exceptional Value classes per target, and the models and mapping files in use. |
| verify_logA | Walk the log's hash chain from the first entry and report whether any entry was altered or removed. |
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 role: listing targets, mapping a record, validating a mapping file, comparing fidelity across mappers, summarizing the log, and verifying log integrity. Although map_record and fidelity both involve mapping a record, their scopes are clearly separated (single target vs. cross-target comparison) and descriptions make the boundary explicit.
Most tools follow a clear verb_noun pattern (list_targets, map_record, check_mapping, log_summary, verify_log), with 'fidelity' being the lone noun-only exception. The set remains readable and predictable overall, but the deviation prevents a perfect score.
Six tools is well-scoped for a mapping and logging server, and each tool appears to earn its place. There is no apparent bloat or missing essential operation at the count level.
The surface covers target listing, mapping, mapping validation, cross-target fidelity comparison, log summarization, and log integrity verification. Minor gaps exist around discovering available models or mapping files, but core workflows are covered and agents can work around these omissions.