us-eli-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| US_ELI_API_KEY | No | API key for Congress.gov API. Get your own free key at https://api.congress.gov/sign-up/ | DEMO_KEY |
| US_ELI_BASE_URL | No | Base URL for the Congress.gov API | https://api.congress.gov/v3 |
| US_ELI_AUDIT_DIR | No | Directory for audit logs | ~/.matematic/audit |
| US_ELI_CACHE_DIR | No | Directory for caching API responses | ~/.matematic/cache/us-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 |
|---|---|
| us_search_billsA | List US federal bills of a given congress and bill type. |
| us_get_billA | Fetch full detail (including latest action/status) for one bill. |
| us_list_code_packagesA | List enacted-law packages in a GovInfo collection modified since a given date. |
| us_get_code_packageA | Fetch metadata and content-format download links for one GovInfo package. |
| us_search_federal_registerA | Full-text search over Federal Register documents (1994-present, keyless). |
| us_get_federal_register_docA | Fetch full metadata for one Federal Register document. |
| us_search_case_lawA | Full-text search over 8M+ US court opinions (CourtListener, keyless). The headline value is STATE case law - no other tool in this server covers state courts. Federal courts are searchable too, but dedicated CourtListener MCP wrappers exist for heavy federal case-law work. |
| us_get_caseA | Fetch one opinion cluster by its CourtListener Uses the keyless search endpoint with a |
| us_search_cfr_sectionsA | Full-text search over the CURRENT Code of Federal Regulations (eCFR, keyless). Unlike the GovInfo |
| us_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:
|
| us_get_cfr_section_historyA | Fetch the amendment history (point-in-time versions) of one CFR section. |
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 11 tools
Each tool targets a distinct legal source and action: bills, code packages, Federal Register, case law, CFR sections, and a coverage tool. The search/get pairs are clearly separated by resource type, and even similar regulatory sources (Federal Register vs CFR) are distinct.
All tools follow the 'us_' prefix with a verb_noun pattern (search_, get_, list_). The only outlier is 'us_coverage', which uses a noun instead of verb_noun, and 'get_case' is shorter than 'get_federal_register_doc', but overall the pattern is consistent and predictable.
11 tools is well-scoped for a legal research connector covering multiple sources. Each tool serves a clear purpose, and the count is within the ideal 3-15 range, not feeling bloated or sparse.
The server provides search and retrieval for each major legal source: bills, code packages, Federal Register, case law, and CFR. The coverage tool explicitly identifies gaps and fallbacks, which mitigates incompleteness. Minor missing operations like a direct 'get CFR section' tool are workable through search and history tools.