cordata-catalog-mcp
OfficialServer 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.
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_domainsA | What domains exist, and who owns them. Only the domains this caller may read. |
| get_datasetB | Schema, ownership and policy tags for one published dataset. |
| resolve_lf_tagA | Is this tag set valid against the governance-owned ontology? Runs the same |
| check_grant_expressionB | Would this tag-based grant expression reach this dataset, and which columns? |
| find_datasetsA | Which datasets carry these tag values — for example subject_type=customer. Answers which datasets hold a kind of data, and in which columns. It cannot say where one person's rows are: that is a query against the data, and this server never reads data. Only domains this caller may read. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| lf-tag-ontology | The governance-owned LF-tag vocabulary every tag is checked against. |
TDQS
Scored across 5 tools
Most tools have clearly distinct purposes: listing domains, validating tags, checking grant expressions, finding datasets, and fetching one dataset. However, resolve_lf_tag and check_grant_expression both involve policy evaluation and could be confused without careful reading of their descriptions.
All names follow a consistent snake_case verb_noun pattern: list_domains, resolve_lf_tag, check_grant_expression, find_datasets, get_dataset. Minor singular/plural variations are semantically appropriate rather than inconsistent.
Five tools is well-scoped for a read-only catalog and governance server. Each tool covers a distinct capability—domain listing, tag validation, grant checking, dataset search, and dataset retrieval—without redundancy.
The surface covers core read-only governance queries but lacks a way to enumerate all datasets (e.g., list_datasets by domain or without tags) and has no tools for listing tags, ontologies, or policies. These notable gaps could block an agent trying to browse the catalog comprehensively.