GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者による説明(英語の原文)
Quota-guarded MCP layer over Korean public data APIs (data.go.kr), compiled from OpenAPI specs
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"mcportal": {
"command": "uvx",
"args": [
"mcportal"
]
}
}
}ターミナルでこれを実行します
claude mcp add mcportal -- uvx mcportalプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"mcportal": {
"command": "uvx",
"args": [
"mcportal"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"mcportal": {
"type": "stdio",
"command": "uvx",
"args": [
"mcportal"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月8日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント yonghwan1106 で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.2.2)がレジストリに届いたのは3 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにPython (uv)も必要です。
同じカテゴリには:GitHub, Desktop Commander, Cloudflare MCP
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:↓ 週あたりのダウンロードi★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
The missing bridge between data.go.kr and the global MCP ecosystem. MCPortal normalizes Korean public-API specifications into standard OpenAPI 3.1, compiles them into MCP servers, and puts every outbound call behind a hard daily budget with backoff and caching. Fully open source, fully self-hosted.
한국어 문서: README.ko.md — this English README is the canonical document and the Korean file is a translation of it.
Accuracy disclaimer
data.go.kr publishes no "remaining quota" endpoint. MCPortal's usage ledger
therefore counts only the calls that went through MCPortal, which makes it
a best-effort estimate. Calls that the same
serviceKeyspends outside
MCPortal — another script, the portal console, a different tool — never reach
the ledger, so the ledger value is always a lower-bound approximation of real
consumption. The axis of trust is not that estimate but the **hard budget cap
(
CALL_BUDGET)**. Even when the ledger is wrong, the hard guard physically
blocks calls beyond the daily cap, so the safety line against quota-related
account sanctions always comes from
CALL_BUDGET.
| Works without any API key | Needs a data.go.kr service key |
|---|---|
| Replaying record/replay cassettes | Live API calls |
The full test suite (pytest), including the record-mode tests, which run on synthetic transports | Live response sampling |
Standing up an MCP server from a committed spec plus its cassette (mcportal serve --replay) — from a repo checkout, or from a PyPI install pointed at one (note 1) | Ad-hoc conversion of an API that has no cassette yet |
Regenerating the compile demo (examples/compile_demo.py) | Recording new cassettes |
Regenerating and listing the preset bundles (mcportal compile / mcportal presets) — bundled in the wheel since 0.2.0 (note 1) | Sampling a response schema that is still unresolved (mcportal sample) |
Reading quota status (mcportal quota status) | The key-dependent benchmark items K1–K3 |
Running the benchmark harness (the five key-free items in benchmarks/PROTOCOL.md) | — |
Every demo, development and CI path in MCPortal runs without a key. The record/replay layer replays cassettes that were recorded earlier, so the same response flow can be reproduced and the whole test suite can go green with no serviceKey present. Spec-to-MCP conversion has already happened at build time — the compiled artifacts are committed under specs/ — so clone the repository and even standing up an MCP server and answering tool calls needs no key: mcportal serve 15000115 --replay serves eight tools over stdio with no serviceKey anywhere in the environment.
That sentence says *clone* on purpose. Replay needs a cassette, and cassettes are recorded upstream responses that stay in the repository instead of going out in the wheel (note 1), so a bare pip install mcportal has nothing to replay until it is pointed at a checkout with --presets-root or MCPORTAL_PRESETS= . Cassettes exist for three of the four bundles — 15081808 has none in the repository either, because it was deliberately left out of sampling (see *Presets* below), so that one bundle is live-only.
What does need a key is narrow: live traffic to data.go.kr, and sampling or converting an API that has no cassette yet.
Note 1 — what the wheel carries, and what it does not.
Since 0.2.0, the published wheel carries the four preset bundles (16 bundle
files plus the two
presets/documents, measured on the built artifact), so a
plain
pip install mcportalcan runmcportal presetswith no checkout.
Since 0.2.2 the wheel also carries the three
sampled_schemas.jsonfiles
—
15000115,15101612and15102108;15081808has none, because it was
deliberately left out of sampling. They ship because `mcportal compile
--check
needs them:--check` does not diff files, it re-synthesizes
openapi.jsonfrom its source + curation + sampled layers, so without the
sampled layer an installed copy cannot reproduce the very
openapi.jsonit
shipped. On 0.2.1 as published,
compile --checkfrom a plain install reports
3 of 4 drifted and exits 3 (measured 2026-08-15); on that version pass
--presets-root /presets. 0.2.2 restores it to 4 of 4 matched,
exit 0, from the install alone.
Those three files carry only the **field names and types inferred from the
responses** — zero response values — and that structure already ships inside
openapi.json, so nothing is exposed that the wheel did not already carry.
What the wheel still leaves out is the recorded upstream traffic itself:
`cassettes/` and `samples/` stay in the repository only, which is why
mcportal serve --replayis a checkout path. To use a different bundle set —
or to give a PyPI install the cassettes — point MCPortal at a checkout with
--presets-rootor the environment variableMCPORTAL_PRESETS=.
When
mcportal presetsfinds no bundle it prints the paths it searched.
# 1) Compile a spec from synthetic fixtures (zero network, zero credentials).
python examples/compile_demo.py
mcportal serve 15000115 --replay
#
python -c "from mcportal.mcp import build_server; \ build_server('specs/demo/openapi.json', mode='replay', \ cassette_path=' ')"
mcportal presets # list mcportal compile --check # byte-compare committed vs regenerated (exit 3 on drift)
pytest -q
pip install mcportal # core runtime (single dependency: httpx)
pip install "mcportal[mcp]" # + the MCP conversion layer (fastmcp)
Dependency policy: the core runtime depends on httpx and nothing else. The spec-normalizing compiler (mcportal.compiler) uses only the standard library and httpx. fastmcp is required solely by mcportal.mcp and ships as the optional [mcp] extra — without it, import mcportal and the entire test suite still work, and calling into the MCP layer raises a Korean ImportError that explains how to install it. The [mcp] extra also declares anyio, because the sync-to-async bridge imports anyio.to_thread directly; httpx pulls anyio in transitively, but a direct import deserves a direct declaration so that pins and lockfiles constrain it.
import mcportal does not import mcportal.mcp — that is what keeps the import working without fastmcp installed. The MCP symbols are resolved lazily on first attribute access through a module __getattr__ (PEP 562), so from mcportal.mcp import build_server and mcportal.build_server refer to the same object. Either spelling is fine.
MCPortal's data.go.kr profile does not support multi-key rotation. data.go.kr issues one key per development account and meters a daily call limit against it; cycling several keys to escape that limit risks violating the service's operating policy and inviting account sanctions. MCPortal respects the structure as it is and accepts a single key. When the limit is too low, the supported answer is data.go.kr's own path — registering a use case and applying for the operational tier — not more keys.
The CLI uses the standard library argparse only. Zero new runtime dependencies is a binding rule for this project, so even the terminal tables are laid out by hand (Hangul counted as double width, ASCII rules, safe on a Windows cp949 console).
mcportal quota status [--ledger PATH] [--budget N] [--day YYYY-MM-DD]
[--key-fp FP | --key-env VAR] [--json] mcportal compile [PRESET_ID ...] [--presets-root PATH] [--check] [--json] mcportal presets [--presets-root PATH] [--json] [--verbose] mcportal sample PRESET_ID ... --key-env VAR [--budget N] [--count N] [--ledger PATH] [--presets-root PATH] [--json] mcportal serve PRESET_ID [--replay | --key-env VAR] [--presets-root PATH] [--name TEXT]
| Subcommand | What it does |
|---|---|
quota status | Shows today's (KST) usage, budget, remainder and state per key fingerprint. The ledger is opened read-only (`mode=ro`) and never created. Budget resolution order is --budget > CALL_BUDGET > profile default, and the output states which path was taken |
compile | Regenerates preset bundles. Files whose content is unchanged are not rewritten. --check writes nothing and only byte-compares |
presets | Lists the bundles as a table; --verbose expands the curation notes |
sample | Live sampling that fills in response schemas still marked unresolved, writing the inferred schema, the response bodies and a replayable cassette. It is the one subcommand that needs a key, and the key is taken only from the environment variable named by --key-env VAR, never as a literal argument |
serve | Stands one bundle up as an MCP server over stdio. The default --replay needs no key; --key-env VAR goes live through the same quota guard. Requires the [mcp] extra. Documented against a repo checkout: --replay reads presets/ /cassettes/ .json, which the wheel does not carry (note 1), so from a PyPI install pass --presets-root /presets or set MCPORTAL_PRESETS= /presets. Three of the four bundles have a cassette — 15081808 has none in the repository either, so it serves live only. stdout is protocol-only; every human-readable line, banner included, goes to stderr |
Exit codes: 0 success (including "no ledger", "no presets" and "nothing changed" — an empty state is not a failure) / 1 execution failure / 2 usage error / 3 drift found by compile --check / 130 user interrupt.
--json prints JSON alone on stdout (no human prose mixed in, so it is pipe-safe) and sends every error to stderr. A raw service key is never printed on any path — even --key-env reads the environment variable and computes the fingerprint locally. The ledger stores no raw key, so a fingerprint is the only thing the CLI ever had available to show.
presets/ holds bundles built from real published specifications on data.go.kr. Their purpose is to demonstrate, in data rather than in code, the fix for the failure mode of naive spec conversion, where every generated tool ends up described as "list query".
| ID | Service | Domain | Sour
冒頭だけを表示しています。続きはリポジトリで読めます