MCP

Seven tools, one server.

Expose every domain to any MCP client. Tool descriptions carry the routing hints — “legal, regulatory, compliance questions go here” — so the upstream agent routes itself.

BuildingThe MCP server ships with 1stAuthor Law. The configuration below is final; the endpoint goes live with it.

claude mcp add --transport http 1stauthor https://mcp.1stauthor.com/mcp \
  --header "Authorization: Bearer YOUR_KEY"

{
  "mcpServers": {
    "1stauthor": {
      "url": "https://mcp.1stauthor.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_KEY" }
    }
  }
}

from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async with streamablehttp_client(
    "https://mcp.1stauthor.com/mcp",
    headers={"Authorization": "Bearer YOUR_KEY"},
) as (read, write, _):
    async with ClientSession(read, write) as s:
        await s.initialize()
        r = await s.call_tool("ask", {"query": "网络刷单诈骗三万元，未遂，量刑区间", "scope": "both"})
        print(r.content[0].text)

Tools

papers_search	Hybrid search over full-text papers with database-style filters. Returns briefs, not answers.
papers_read	Read a paper in layers: brief, head, one section, or raw.
law_search	Article-level retrieval over statutes from 26 jurisdictions. Filters by jurisdiction, law, domain, status, date.
law_read	One article with translation and extraction, its context window, a chapter, or the full law.
case_search	Retrieve Chinese judgments by cause, court, date, cited article, amount, sentence. Carries a coverage block.
case_read	A judgment in layers: brief, head, opinion, decision, raw. Also the articles it cites.
ask	Agentic search: a question in, a cited answer out. scope=auto routes to papers, law or cases.

An agent handed a bare ask(query) tool will use this API poorly. These three distinctions belong in your tool descriptions. Read the docs →