ca-eli-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CA_ELI_BASE_URL | No | Base URL of the Justice Laws Website. | https://laws-lois.justice.gc.ca |
| CA_ELI_AUDIT_DIR | No | Directory for audit logs. | ~/.matematic/audit |
| CA_ELI_CACHE_DIR | No | Directory for caching. | ~/.matematic/cache/ca-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 |
|---|---|
| ca_get_documentB | Fetch metadata for a Canadian federal act or regulation. |
| ca_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:
|
| ca_get_textA | Fetch the full consolidated XML text of a Canadian federal act or regulation. |
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 3 tools
Each tool has a clearly distinct purpose: ca_get_document returns metadata, ca_get_text returns full XML content, and ca_coverage declares connector limitations. There is no meaningful overlap or ambiguity between them.
ca_get_document and ca_get_text follow a consistent ca_get_noun pattern, but ca_coverage breaks the pattern by omitting the verb. The shared ca_ prefix keeps the set recognizable, and no mixed casing styles are present.
Three tools is well-scoped for a focused read-only legislation retrieval server. Each tool serves a distinct role and there is no redundancy.
The server covers metadata retrieval, full-text retrieval, and coverage declarations, but lacks any search or listing capability for discovering acts and regulations. Users must already know the exact document identifier, which is a notable gap; the ca_coverage tool mitigates but does not eliminate this limitation.