us-law-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GOVINFO_API_KEY | No | Your GovInfo API key. If not set, U.S. Code queries fall back to Cornell LII (slow and unofficial). Available at https://api.data.gov/signup/ | |
| CONGRESS_API_KEY | No | Your Congress.gov API key. If not set, bill and public law lookups are limited. Available at https://api.congress.gov/sign-up/ | |
| COURTLISTENER_TOKEN | No | Your CourtListener token. If not set, case search and citation checking still work, but full text of recent opinions is unavailable. Available at https://www.courtlistener.com/help/api/rest/ | |
| US_LAW_ENABLE_LII_FALLBACK | No | Set to 'false' to disable the Cornell LII fallback for U.S. Code when GovInfo is unavailable. Defaults to 'true'. | true |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| legal_researchA | Run a multi-step legal research chain in one call. Combines statute, regulation and case-law lookups and reports every step's outcome, including steps that found nothing. Use task to pick the shape of the research; task=document_review verifies every citation in text you supply. |
| legal_analysisA | Verification and analysis over U.S. law. mode=verify_citations checks every citation in a block of text against primary sources and flags fabricated or misdescribed authority — run it on any AI-drafted legal text before relying on it. mode=cite_check reports whether a decision has been overruled. mode=applicable_law returns the version of a statute or rule in force on a past date. mode=impact_map shows what cites a provision. |
| search_lawA | Search federal statutes (U.S. Code). Accepts a citation, a popular name or acronym (Section 230, ADA, FOIA, RICO, Title VII), or free-text keywords. Returns the citation, official section heading and the identifiers needed by get_law_text. Use this first when you need a statutory basis. |
| get_law_textA | Retrieve the operative text of a U.S. Code section. Accepts either a citation string or title+section. Reports which edition supplied the text and how current it is, so superseded language is not mistaken for current law. Pass full=true for the complete section including notes. |
| search_regulationsA | Search federal regulations (Code of Federal Regulations) by citation or keyword, and surface recent Federal Register rulemaking that affects the matched part. Use for agency requirements, permits, thresholds and compliance obligations — statutes live in search_law. |
| get_regulation_textA | Retrieve the text of a CFR section (or part-level metadata) from eCFR. Pass date=YYYY-MM-DD to get the version in force on that day — use this whenever the question concerns past conduct, because the current text may differ. Includes amendment history and the part's authorising statutes. |
| regulatory_radarA | Check whether a CFR part has fallen behind the statutes it was issued under. Reads the part's Authority note, finds when each authorising statute was last amended, compares that against when the rule was last revised, and flags any statute that moved afterwards. Use for compliance review and for spotting rules that may no longer match their authority. |
| search_decisionsA | Search U.S. court decisions (CourtListener, 9M+ opinions across federal and state courts). Accepts a case name, a reporter citation, a docket number, or issue keywords. Use domain to restrict the court tier. Returns citations, cite counts and the ids needed by get_decision_text. |
| get_decision_textA | Retrieve the full text of a court decision by citation, CourtListener cluster/opinion id, or case name. Separates majority, concurring and dissenting opinions. Long opinions are compacted by default — pass full=true for everything. |
| discover_toolsA | Search the full tool catalog, including specialist tools that are not advertised in tools/list. Returns each match with its parameters so you can invoke it through execute_tool. Call this when none of the listed tools fits. |
| execute_toolA | Run any tool from the catalog by name with an arguments object. Use after discover_tools to reach specialist tools that are not advertised in tools/list. Advertised tools can also be called this way, though calling them directly is simpler. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/seelpeed-debug/us-law-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server