Skip to main content
Glama
README.md
# @pipeworx/tw-fsc-actions

Has Taiwan's Financial Supervisory Commission (金融監督管理委員會) penalised this firm? The FSC publishes the decisions (裁處書) it classes as major penalty cases (重大裁罰案件) from 2012: about 500 against banks, insurers, securities and futures firms, investment trusts, insurance agents and brokers. Firms only.

Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 2020+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

## Tools

- `tw_fsc_enforcement_search(query?, date_from?, date_to?, bureau?, page?, limit?)` -- the FSC matches `query` on the case title (Chinese); `date_from` and `date_to` filter the decision date. Each case gives the id, decision date, issuing bureau (銀行局, 保險局, 證券期貨局, 檢查局), the firm, the title as published (the breach and the sanction), document numbers, the sanction words found in the title and the link to the official decision. Also returns `total_matching`, `searched` and `data_as_of`.
- `tw_fsc_enforcement_get(id)` -- one case by its 12-digit id: the firm, decision date and document number, the purpose and decision (主旨) and the facts, in Chinese. An unknown id returns `found: false`.

## Auth

Keyless.

## Data sources

- Taiwan Financial Supervisory Commission (金融監督管理委員會), major penalty cases (重大裁罰案件). Read from the publisher on each call; nothing is stored.

## Individuals are not returned

Cases whose subject is not clearly a firm (a masked personal name such as 張○○, or a name that carries no company word) are left out and counted in `skipped_possible_individuals`. Masked personal names inside a firm's own title or decision are replaced with [個人], and the representative named on a decision is not returned. Every response carries a `note` saying so; the tests prove that a person's name never appears.

## Behaviour worth knowing

- The FSC lists only the cases it classes as major, so a firm with no case here may still have been penalised.
- The firm name is read from the opening words of the case title; for odd titles it can include a trailing word.
- A page without the list layout (a redesign or a challenge page) is refused as `upstream_down`, never read as empty.
- No match says what was searched (`empty_reason`).

## Quick Start

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

```json
{
  "mcpServers": {
    "tw-fsc-actions": {
      "url": "https://gateway.pipeworx.io/tw-fsc-actions/mcp"
    }
  }
}
```

### What this endpoint actually serves

`tools/list` at `https://gateway.pipeworx.io/tw-fsc-actions/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 2020+ 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/tw_fsc_enforcement_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"證券","date_from":"2025-06-01","limit":3}'
```

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

## Run it from npm

`@pipeworx/mcp-tw-fsc-actions` is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with `npx`, and it forwards every call to the same
`https://gateway.pipeworx.io/tw-fsc-actions/mcp` endpoint shown above. It needs network access;
there is no offline mode.

```json
{
  "mcpServers": {
    "tw-fsc-actions": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-tw-fsc-actions"]
    }
  }
}
```

Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
`"env": { "PIPEWORX_API_KEY": "<your key>" }` to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.

It lists **only** this pack's tools by default. Set `PIPEWORX_META_TOOLS=1` to
also list `ask_pipeworx` and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in `fetch` does not read `HTTPS_PROXY` by
default. Newer Node releases honour it when `NODE_USE_ENV_PROXY=1` is set; check
your Node version's documentation.

## 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 Tw Fsc Actions data" })
```

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

## More

- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)

## License

MIT