Skip to main content
Glama
README.md
# @pipeworx/kr-pipc-actions

Has South Korea's Personal Information Protection Commission (개인정보보호위원회)
announced enforcement against this company: an administrative fine (과징금,
과태료), a corrective order (시정명령), a publication order or a sanction after a
personal-data breach?

Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 2018+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

## Tools

- `kr_pipc_actions_list(page?, pages?, name?)` — one page (ten releases) of the
  commission's press releases per page number, up to 3 consecutive pages, newest
  first. Enforcement releases are returned with date, title (usually the company or
  the number of companies), issuing department and an `ntt_id`; releases that are not
  enforcement are counted in `non_enforcement_dropped`. `name` keeps rows whose title
  contains it. Also returns `result` (`rows`, `no_title_match_on_pages_read`,
  `no_enforcement_release_on_pages_read`, `beyond_last_page`), `pages_read`,
  `releases_scanned`, `last_page`, `coverage` and `data_as_of`.
- `kr_pipc_actions_read(ntt_id)` — one release as plain text: the companies fined or
  ordered, the amounts, the breach found and the orders made. Phone numbers, e-mail
  addresses and sole-trader (개인사업자) names are removed and counted in
  `redactions`. `body_present` is false when the release carries no text on its page.

## Auth

Keyless.

## Data sources

- Personal Information Protection Commission (개인정보보호위원회), press releases,
  read from the publisher on request. Page numbers are the commission's own.
  `data_as_of` is the day of the read.

## Behaviour worth knowing

- Firms only. Individuals' contact data and sole-trader names are removed and
  counted, never returned.
- A name search looks only at titles on the pages read. A company named only inside
  a release body is not found by `kr_pipc_actions_list`; read the release. No row is
  not a clearance of the company, and `coverage` says which pages were read.
- Titles that give a count ("2 operators") rather than a name are listed as they are;
  the names are in the release text.
- A page without the expected markup or an HTTP failure is refused, so a source that
  cannot be read is never reported as "no enforcement found".

## Quick Start

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

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

### What this endpoint actually serves

`tools/list` at `https://gateway.pipeworx.io/kr-pipc-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 2018+ 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/kr_pipc_actions_list \
  -H 'Content-Type: application/json' \
  -d '{"page":1,"name":"삼양"}'
```

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

## Run it from npm

`@pipeworx/mcp-kr-pipc-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/kr-pipc-actions/mcp` endpoint shown above. It needs network access;
there is no offline mode.

```json
{
  "mcpServers": {
    "kr-pipc-actions": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-kr-pipc-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 Kr Pipc 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