lt-eli-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LT_ELI_BASE_URL | No | The base URL for the data.gov.lt API. | https://get.data.gov.lt |
| LT_ELI_AUDIT_DIR | No | Directory for audit logs. | ~/.matematic/audit |
| LT_ELI_CACHE_DIR | No | Directory for caching responses. | ~/.matematic/cache/lt-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 |
|---|---|
| lt_searchA | Search Lithuanian acts whose title contains a substring. |
| lt_get_actA | Fetch Lithuanian act metadata by its TAR code. |
| lt_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:
|
| lt_get_textA | Fetch the full Lithuanian text of an act by its TAR code. |
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 4 tools
Each tool has a clearly distinct function: search by title, fetch metadata by TAR code, fetch full text by TAR code, and declare coverage. There is no overlap or ambiguity between them.
All tools share the lt_ prefix, and three follow a verb_noun pattern (lt_search, lt_get_act, lt_get_text). However, lt_coverage breaks the pattern by being a noun, making the naming slightly inconsistent.
Four tools is well-scoped for a focused legal retrieval server. Each tool covers a distinct and necessary part of the workflow without unnecessary bloat.
The set provides a complete retrieval lifecycle: search to find acts, fetch metadata, fetch full text, and a coverage tool that explicitly documents gaps with fallbacks. No obvious dead ends or missing core operations.