CBI Data 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.
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_programmesB | Read-only list programmes. Preserve evidence dates, conditions, coverage gaps and warnings. Missing context never establishes eligibility or a travel waiver. |
| get_programmeC | Read-only get programme. Preserve evidence dates, conditions, coverage gaps and warnings. Missing context never establishes eligibility or a travel waiver. |
| compare_programmesC | Read-only compare programmes. Preserve evidence dates, conditions, coverage gaps and warnings. Missing context never establishes eligibility or a travel waiver. |
| get_programme_costsC | Read-only get programme costs. Preserve evidence dates, conditions, coverage gaps and warnings. Missing context never establishes eligibility or a travel waiver. |
| get_travel_ruleC | Read-only get travel rule. Preserve evidence dates, conditions, coverage gaps and warnings. Missing context never establishes eligibility or a travel waiver. |
| get_sourceC | Read-only get source. Preserve evidence dates, conditions, coverage gaps and warnings. Missing context never establishes eligibility or a travel waiver. |
| get_changesC | Read-only get changes. Preserve evidence dates, conditions, coverage gaps and warnings. Missing context never establishes eligibility or a travel waiver. |
| get_coverageC | Read-only get coverage. Preserve evidence dates, conditions, coverage gaps and warnings. Missing context never establishes eligibility or a travel waiver. |
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 8 tools
Each tool name targets a distinct facet (listing vs single programme, comparison, costs, travel rules, sources, changes, coverage), so an agent can route sensibly. However, every description is the same boilerplate text, so the names alone carry the differentiation burden, and get_programme_costs / get_coverage have some conceptual overlap.
All eight tools follow a strict snake_case verb_noun pattern using list_, get_, and compare_ prefixes with a single consistent noun for the resource. No style mixing or ad-hoc names anywhere in the set.
Eight tools is a well-scoped size for a read-only reference-data server. Each tool maps to a distinct data facet, and there is no redundant filler.
The surface covers the lifecycle of read-only reference work: enumerate, inspect, compare, plus costs, travel rules, provenance (source), change history, and coverage gaps. A free-text search or a bulk multi-programme filter is missing, but agents can work around it via list_programmes and compare_programmes.