eu-reg-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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_micar_registerA | Search the ESMA interim MiCAR register by entity name or LEI. query: entity-name substring (case- and accent-insensitive) or an exact LEI. Each result carries its entry_id and the ESMA source file; the response states the snapshot date, data_age_days and a stale flag. register_slug: all | other-wp | emt-wp | art-wp | casps | ncasp. member_state: optional two-letter code (DE, IE, MT, ...). offset: skip this many matches (results come 25 at a time; see truncated). |
| micar_register_summaryB | Current totals per MiCAR register and white paper format coverage. |
| micar_register_changesB | Recent register movement: new filings, changed entries, removals. change_type: all | added | changed | removed. Each record says whether the entry is still listed in the latest snapshot. |
| lint_micar_whitepaperA | Lint a draft MiCAR white paper (JSON) against Annex I-III rules. Returns cited candidate findings pending human review. Requires the
optional |
| classify_eu_ai_act_systemA | Classify an AI system's EU AI Act risk tier with pinpoint citations. Pass a SystemProfile as JSON; pass an empty string to get the schema.
Requires the optional |
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 5 tools
Each tool has a clearly distinct purpose: search the register, get a summary, see recent changes, lint a whitepaper, or classify an AI system. There is no overlap in functionality between tools.
All names use snake_case consistently, but the pattern is mixed: some are verb_noun (search_micar_register, lint_micar_whitepaper, classify_eu_ai_act_system) while others are noun phrases (micar_register_summary, micar_register_changes). Token order also varies (search_micar_register vs. micar_register_summary), a minor deviation.
Five tools is well-scoped for a focused regulatory data server; each tool earns its place by addressing a distinct need (search, summary, changes, lint, classify).
The search tool returns an entry_id but there is no companion tool to fetch full entry details, creating a dead end. AI Act coverage is limited to a single classification tool, leaving notable gaps for a server that otherwise covers MiCAR register operations.