ListRiver

io.github.ListRiver-LLC由 GitHub 账号 ListRiver-LLC 发布v0.1.0更新于 Nov 7, 2026

从州注册库中搜索美国新成立和活跃的企业：按州、城市、ZIP、NAICS查找新成立的LLC。

AI 翻译由 AI 模型根据下方的原文描述翻译，可能有误。

原文描述

Search new and active U.S. businesses from state registries: new LLCs by state, city, ZIP, NAICS.

已验证STDIO仅桌面

概览

ListRiver 的本地 MCP 服务；无需登录；STDIO；3 个工具。

暂无 AI 概览：以下信息来自注册中心条目和服务本身。

安装

在 SourceWeft 中

  1. 打开 控制台中的 ListRiver，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

ListRiver MCP server

Lets Claude and other AI assistants search new and active U.S. businesses from official state business registries through ListRiver: new LLCs, corporations and nonprofits by state, city, county, ZIP, NAICS industry, entity type, formation month, and whether a phone or email is on file.

Ask things like:

  • "How many businesses were formed in Miami-Dade in the last 3 months that have a phone number?"
  • "Find 20 new construction companies in Harris County, Texas."
  • "List new LLCs in ZIP 80202 formed this month, with their registered agents."

Tools

ToolWhat it doesCost
list_statesStates covered and their record countsfree
count_businessesHow many businesses match a search, per statefree
search_businessesThe matching businesses (25 by default, up to 100 per call; cursor for more)each business returned counts against your ListRiver records

The assistant is told to count first and to ask only for as many businesses as you need.

Setup

  1. Get a free API key (500 records a month): listriver.com/Account/ApiSignUp.aspx
  2. Install uv (it runs the server with uvx, no other install needed).
  3. Add the server to your AI app.

Claude Desktop (Settings > Developer > Edit Config, then restart Claude Desktop):

json
{  "mcpServers": {    "listriver": {      "command": "uvx",      "args": ["listriver-mcp"],      "env": { "LISTRIVER_API_KEY": "lr_key_..." }    }  }}

Claude Code:

bash
claude mcp add listriver -e LISTRIVER_API_KEY=lr_key_... -- uvx listriver-mcp

Other MCP clients: run uvx listriver-mcp (stdio) with LISTRIVER_API_KEY in the environment. Or pip install listriver-mcp and run listriver-mcp.

Source

The server is listriver_mcp/server.py in this folder (Python, built on the official MCP Python SDK, using the listriver client from this repository). Tests: tests/test_server.py.

Run from a clone of the repository:

bash
pip install ./python ./mcpLISTRIVER_API_KEY=lr_key_... listriver-mcp

or build the Dockerfile at the repository root: docker build -t listriver-mcp . then docker run -i --rm -e LISTRIVER_API_KEY=lr_key_... listriver-mcp.

Notes

  • Every business returned counts against your records each time it is returned; repeated or overlapping searches count again. Counting is free.
  • Phone, email, NAICS and county are on file for only part of the records, and coverage varies by state.
  • The data is for your own business use, not for resale or for credit, insurance, employment or housing decisions (ListRiver API agreement).
  • More: API documentation - [email protected]

MIT license.

来源：mcp/README.md，提交 7ea090c

工具

3

list_states

List the states ListRiver covers, with how many businesses each has: formed this month or last ("recent"), in the last 12 months ("year"), and every active business ("all"). Free.

无需输入参数。

count_businesses

Count businesses matching the filters, per state. Free: use it before search_businesses. Args: states: Comma-separated two-letter registration states, e.g. "FL" or "FL,TX". Required with city, county or zip. city: Comma-separated business cities, e.g. "MIAMI". county: Comma-separated counties, e.g. "MIAMI-DADE" (or "FL:MIAMI-DADE"). zip: Comma-separated 5-digit ZIP codes or 3-digit ZIP prefixes, e.g. "33139,331". naics: Comma-separated NAICS prefixes, 2-6 digits, e.g. "23" (construction) or "722511". entity_type: Comma-separated of LLC, CORP, LP, LLP, NONPROFIT, OTHER. has_phone: Only businesses with a phone number on file. has_email: Only businesses with an email on file. formed_within: Formed in the current month or the N months before it (1 = this month or last). Set 0 for any formation date. formed_from: First formation month, "YYYY-MM" (overrides formed_within). formed_to: Last formation month, "YYYY-MM" (overrides formed_within).

输入参数zipcitynaicscountystatesformed_tohas_emailhas_phoneentity_typeformed_fromformed_within

search_businesses

Get businesses matching the filters (same filters as count_businesses). USES THE USER'S RECORDS: each business returned counts, every time it is returned, so ask only for what the user needs. Args: states: Comma-separated two-letter registration states. Required with city, county or zip. city: Comma-separated business cities. county: Comma-separated counties. zip: Comma-separated 5-digit ZIP codes or 3-digit prefixes. naics: Comma-separated NAICS prefixes, 2-6 digits. entity_type: Comma-separated of LLC, CORP, LP, LLP, NONPROFIT, OTHER. has_phone: Only businesses with a phone number on file. has_email: Only businesses with an email on file. formed_within: Formed in the current month or the N months before it (1 = this month or last; 0 = any date). formed_from: First formation month, "YYYY-MM". formed_to: Last formation month, "YYYY-MM". limit: How many businesses to return, 1-100 (default 25). cursor: The cursor from a previous search_businesses answer, to get the next businesses of the same search.

输入参数zipcitylimitnaicscountycursorstatesformed_tohas_emailhas_phoneentity_typeformed_from另有 1 个

版本历史

1
  1. v0.1.0最新Nov 3, 2026

评分

已满足适用检查项的 80%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。