jp-eli-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JP_ELI_BASE_URL | No | Base URL for the e-Gov law search API. | https://laws.e-gov.go.jp/api/2 |
| JP_ELI_AUDIT_DIR | No | Directory for audit logs. | ~/.matematic/audit |
| JP_ELI_CACHE_DIR | No | Directory for caching API responses. | ~/.matematic/cache/jp-eli |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jp_search_lawsA | Search Japanese laws by (partial) title. |
| jp_search_by_keywordA | Full-text search across all Japanese laws for a keyword. |
| jp_get_lawA | Fetch metadata for a law by its e-Gov |
| jp_get_articleA | Fetch the text of one article of a law. |
| jp_coverageA | Declare what this connector covers, how it is sourced, and what it does NOT cover. Call this before telling a user that the law "does not contain" something, and whenever a search comes back empty: the absence may be a gap in this connector rather than in the law. Every gap carries a fallback saying where to look instead. Returns:
|
| jp_get_full_textA | Fetch the full text of a law by |
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 targets a distinct operation: searching by title vs. full-text, fetching metadata vs. a single article vs. full text, and declaring coverage. No two tools overlap in purpose.
All tools follow the consistent pattern jp_<verb>_<noun>, with search/get as verbs and clear nouns. jp_coverage is a slight exception but still fits the jp_ prefix and is a declarative tool, so the pattern remains predictable.
Six tools is well-scoped for a Japanese law retrieval server: two search methods, three retrieval levels (metadata, article, full text), and an explicit coverage declaration. No excess or deficiency.
The core workflows—searching and retrieving law text—are covered. The full-text tool truncates large laws, but jp_coverage explicitly discloses gaps and fallbacks, making the surface reasonably complete for read-only legal access.