il-eli-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IL_ELI_BASE_URL | No | Base URL of the Knesset OData API | https://knesset.gov.il/Odata/ParliamentInfo.svc |
| IL_ELI_AUDIT_DIR | No | Audit directory for logs | ~/.matematic/audit |
| IL_ELI_CACHE_DIR | No | Cache directory for law data | ~/.matematic/cache/il-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 |
|---|---|
| il_search_lawsA | Full-text search over Israeli law names (Hebrew). |
| il_get_lawA | Fetch full detail for one Israeli law by its IsraelLawID. |
| il_search_law_textsA | Search published Israeli law versions (KNS_Law), including consolidated texts. Complements |
| il_get_law_documentsB | Official document files (PDFs) for one published law version. |
| il_search_case_lawA | Keyword search over a local, pre-downloaded corpus of Israeli court judgments. NOT a live API call. The corpus (10,558 Hebrew judgments from Family,
District, Magistrate, Labor, Military and Administrative courts) is a
static HuggingFace dataset ( |
| il_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:
|
| il_get_caseA | Fetch full detail (including full judgment text) for one case by its judgment_id. Reads from the same locally-cached dataset as |
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 7 tools
Each tool targets a distinct resource and action: law metadata, law detail, published law texts, law documents, case law search, case detail, and coverage. The overlapping search tools explicitly clarify the disjoint ID spaces and different underlying registries.
All tools follow a consistent `il_` prefix with verb_noun structure: search_laws, get_law, search_law_texts, get_law_documents, search_case_law, get_case. The only outlier `coverage` is a single non-CRUD utility, still readable and consistent with the prefix pattern.
Seven tools is a well-scoped set for a legal research connector, covering both statutory law and case law without unnecessary overlap. Each tool serves a clear purpose and fits within the typical 3-15 tool sweet spot.
The tool surface provides complete search, retrieval, and document access for both laws and cases. The explicit coverage tool acknowledges gaps and offers fallbacks, making the set robust against missing data and reducing dead ends.