Trademarks

io.github.pipeworx-iov0.1.2更新于 Sep 30, 2026

Trademarks MCP — US trademark search + record lookup

已验证Streamable HTTP可网页运行Web Search & ScrapingBusiness & Commerce

概览

AI 生成的概览

让助手按商标文字检索美国联邦商标，并按序列号或注册号查询记录。

功能
提供四个商标工具：search_trademarks 按文字商标查找已注册和待审的美国商标，可按国际类别和有效/失效状态筛选；get_trademark_by_serial 和 get_trademark_by_registration 返回状态、持有人、日期、商品/服务及分类；get_trademark_documents 返回审查历史，如审查意见和答复。检索覆盖完整 USPTO 注册库且无需密钥。远程网关端点还会额外列出 Pipeworx 共享元工具，包括 ask_pipeworx 路由和 remember/recall。
适用场景
适合在采用某个名称前做品牌清查和初步排查，检查拟用商标是否与现有美国商标冲突，以及按已知序列号或注册号获取详情或审查历史。
运行要求
远程方式：通过 streamable HTTP 连接网关地址，最初几次调用无需账号。本地方式：用 npx 运行该 npm 包，需要 Node.js。按编号查询和文档这三个工具需要 account.uspto.gov 提供的免费 USPTO API 密钥；search_trademarks 无需密钥。
安装前请注意
远程端点除本包工具外还会列出约 30 个 Pipeworx 共享元工具，会增加上下文，并把查询路由到更广的目录；initialize 响应会说明确切范围。USPTO API 密钥是查询和文档工具需要提供的凭据。检索结果仅供参考，不构成法律意见。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Trademarks，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。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "trademarks": {
      "type": "http",
      "url": "https://gateway.pipeworx.io/trademarks/mcp"
    }
  }
}

README

mcp-trademarks

Trademarks MCP — US trademark search + record lookup

Part of Pipeworx — an MCP gateway connecting AI agents to 1684+ live data sources.

Tools

ToolDescription
search_trademarksSearch US federal trademarks by mark text — the clearance/knockout-search path. Find registered and pending marks by wordmark without knowing a serial or registration number, then filter by international class and live/dead status to see which marks are actually enforceable. Covers the full USPTO register (the tmsearch.uspto.gov Elasticsearch backend that replaced TESS). Keyless. Use this to check whether a proposed brand name conflicts with existing US trademarks. Returns wordmark, serial and registration numbers, status, live flag, international classes, goods/services, owner, and filing dates. For a name-availability check, set live_only:true and pass the relevant class (e.g. 35 for advertising/business, 42 for software/SaaS, 9 for downloadable software).
get_trademark_by_serialLook up a US trademark by serial number. Returns status, owner, filing/registration dates, goods/services, and classification. Requires USPTO API key (free at account.uspto.gov).
get_trademark_by_registrationLook up a US trademark by registration number. Returns status, owner, mark text, goods/services, and classification. Requires USPTO API key.
get_trademark_documentsGet the prosecution history (office actions, responses, etc.) for a trademark by serial number. Requires USPTO API key.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

json
{  "mcpServers": {    "trademarks": {      "url": "https://gateway.pipeworx.io/trademarks/mcp"    }  }}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/trademarks/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

json
{  "mcpServers": {    "pipeworx": {      "url": "https://gateway.pipeworx.io/mcp"    }  }}

Both URLs reach the same gateway and the same 1684+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

bash
curl -X POST https://gateway.pipeworx.io/v1/tools/search_trademarks \  -H 'Content-Type: application/json' \  -d '{"query":"TenderBrief","live_only":true,"international_class":"35"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_trademarks. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

json
{  "mcpServers": {    "trademarks": {      "command": "npx",      "args": ["-y", "@pipeworx/mcp-trademarks"]    }  }}

Or run it directly to confirm it starts:

bash
npx -y @pipeworx/mcp-trademarks

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Trademarks data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

来源：README.md，提交 7f81975

工具

0
工具元数据尚未被收录。

版本历史

3
  1. v0.1.2最新Sep 27, 2026
  2. v0.1.1Sep 25, 2026
  3. v0.1.0Sep 16, 2026