mcpField
T
Taiwan Procurement

Taiwan Procurement

Remote
pipeworx.ioLegal & Government0Updated 5w ago

About Taiwan Procurement

Taiwan Procurement provides Taiwan government procurement tender data for procurement research and vendor tracking. It searches by title keyword, company, or date, using a community mirror whose results are best-effort.

Key features

  1. 01Search tenders by title keyword
  2. 02Search bids by company name
  3. 03Retrieve full tender details
  4. 04List tenders by publication date

Use cases

  1. 01Find government tenders on a topic
  2. 02Track a company’s bids or awards
  3. 03Review tenders published on a date

MCP support

As an MCP server, it exposes tools for tender searches, company searches, detail retrieval, and date-based listings. Data comes from the g0v community mirror, so some fields may be blank; it can run through the Pipeworx gateway or locally over stdio.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/taiwan-procurement/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-taiwan-procurement

Taiwan Government Procurement MCP — 政府電子採購網 (PCC) tenders (keyless).

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

ToolDescription
taiwan_search_tendersSearch Taiwan government procurement tenders (政府電子採購網 / PCC) by title keyword, via the g0v community mirror. Pass a keyword (Chinese or English, e.g. "電腦", "AI", "消防"). Returns matching tenders with tender id (unit_id + job_number), title, agency (機關名稱), announcement type, date, and category. Use taiwan_get_tender with a result's unit_id + job_number for full detail. Third-party mirror; results are best-effort.
taiwan_search_by_companySearch Taiwan government procurement tenders (政府電子採購網 / PCC) by company / vendor name — finds tenders a company bid on or was awarded (得標/投標廠商), via the g0v community mirror. Pass a company name in Chinese (e.g. "台積電", "中華電信"). Returns matching tenders with tender id, title, agency, date, and the associated company names/IDs. Third-party mirror; results are best-effort.
taiwan_get_tenderGet full detail for one Taiwan government procurement tender (政府電子採購網 / PCC) via the g0v community mirror. Requires unit_id (機關代碼) and job_number (標案案號), both from a taiwan_search_tenders result. Returns agency contact info, procurement category, budget/award amount, deadlines, and status where available, plus a link to the official PCC page. Third-party mirror; some fields may be blank.
taiwan_list_by_dateList Taiwan government procurement tenders (政府電子採購網 / PCC) published on a given date, via the g0v community mirror. Pass a date as YYYYMMDD (e.g. "20260630"); defaults to today. Returns tenders with id, title, agency, announcement type, and any associated companies. Third-party mirror; results are best-effort.

Quick Start

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

{
  "mcpServers": {
    "taiwan-procurement": {
      "url": "https://gateway.pipeworx.io/taiwan-procurement/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/taiwan-procurement/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:

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

Both URLs reach the same gateway and the same 1683+ 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

curl -X POST https://gateway.pipeworx.io/v1/tools/taiwan_search_tenders \
  -H 'Content-Type: application/json' \
  -d '{"query":"電腦"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/taiwan_search_tenders. 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:

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

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-taiwan-procurement

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 Taiwan Procurement data" })

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

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.