Ask Gina MCPサーバー
コミット 2026年11月2日AIクライアントが、暗号資産トークン、Hyperliquidのパーペチュアル、Polymarketのマーケット、およびユーザーアカウントに関する読み取り専用のリサーチを実行できるようにします。
別名 askgina/plugins, plugins
- スター
- 4
- ツール
- —
- ダウンロード数(30日間)
- —
- 最新バージョン
- 1.0.0
- 最終コミット
- 2026年11月2日
- ライセンス
- Apache-2.0
Ask Gina MCPとは
Ask GinaはMCPサーバーです。 AIクライアントが、暗号資産トークン、Hyperliquidのパーペチュアル、Polymarketのマーケット、およびユーザーアカウントに関する読み取り専用のリサーチを実行できるようにします。.
プロジェクトのREADMEから生成された概要
Ask Gina MCP server について
Ask Ginaは、AIクライアントがさまざまな暗号資産や予測市場にわたって読み取り専用のリサーチを行うための、特化したインターフェースを提供します。エージェントは、暗号資産トークン、Hyperliquidのパーペチュアル、Polymarketのマーケット、および特定のユーザーアカウントを調査できます。このツールは、プログラム可能なインターフェースを通じて、リアルタイムの市場データをAIワークフローに統合する必要がある開発者やリサーチャー向けに設計されています。
ユーザーは、必要な tools:read スコープを持つ、外部で取得したGina bearer tokenを提供することでサービスに接続します。サーバーはログインやOAuth認証を直接処理しないため、クライアント側で必要な認証情報を提供する必要があります。Cursor、Devin、Grok Bot、Antigravity、ChatGPT、Claudeを含む、いくつかの主要なAIホストおよびクライアントと互換性があります。システムはTypeScript SDKとBun CLIを使用して構築されており、データ取得タスクにおいて高いパフォーマンスを実現します。
プロジェクトの README から作成されています。すべてのユースケースは、その引用と照らし合わせて確認されています。
Ask Gina MCPのインストール方法
フォーマット検証日 2026年11月10日Cursor に追加Gooseに追加Claude CodeにAsk Gina MCPをインストール
$ claude mcp add --transport http plugins https://askgina.ai/ai/gina/mcpCursorにAsk Gina MCPをインストール
~/.cursor/mcp.json
{
"mcpServers": {
"plugins": {
"url": "https://askgina.ai/ai/gina/mcp"
}
}
}VS CodeにAsk Gina MCPをインストール
.vscode/mcp.json
{
"servers": {
"plugins": {
"type": "http",
"url": "https://askgina.ai/ai/gina/mcp"
}
}
}VS Code CLIにAsk Gina MCPをインストール
$ code --add-mcp '{"name":"plugins","type":"http","url":"https://askgina.ai/ai/gina/mcp"}'CodexにAsk Gina MCPをインストール
$ codex mcp add plugins --url https://askgina.ai/ai/gina/mcpCodex config.tomlにAsk Gina MCPをインストール
~/.codex/config.toml
[mcp_servers.plugins] url = "https://askgina.ai/ai/gina/mcp"
Gemini CLIにAsk Gina MCPをインストール
$ gemini mcp add -s user --transport http plugins https://askgina.ai/ai/gina/mcpGemini settings.jsonにAsk Gina MCPをインストール
~/.gemini/settings.json
{
"mcpServers": {
"plugins": {
"url": "https://askgina.ai/ai/gina/mcp",
"type": "http"
}
}
}自動チェック
実行日 2026年11月14日完全なレポート →まだ検証されていません。サーバーには80点のスコア、重大な問題がないこと、および検証に必要な十分なデータが必要です。 チェックの仕組み · 点数を上げるための改善点
- ソースリポジトリがリンクされており、アクセス可能askgina/plugins is public and reachablegithub.com/askgina/plugins ↗合格
- パッケージがこのリポジトリをソースとして指定未チェック
- ビルドの来歴 (Sigstore 証明)未チェック
- オープンソースライセンス (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗合格
- 過去1年以内にコミットまたはリリースありLast commit or release 2026-11-02github.com/askgina/plugins ↗合格
- OpenSSF Scorecard未チェック
- パッケージ名が有名なパッケージに酷似していない未チェック
- パッケージおよびその依存関係に重大な勧告なし未チェック
- モデルへの隠れた指示がない0 tool descriptions and the README read; no override phrases, credential paths or hidden characters合格
- 破壊的なツールがラベル付けされている未チェック
- リモートエンドポイントが MCP ハンドシェイクに応答Endpoint did not answer initialize: HTTP 404検出事項
README
GitHubで見るaskgina/plugins
What this is: the Apache-2.0 workspace for the Ask Gina programmatic client (a TypeScript SDK and a Bun CLI), the listed plugin (a portable core plus host adapters), the evals that check whether models use that plugin correctly, and the public evals app. It does not log you in: SDK and CLI callers bring their own token (see below).
Production Gina MCP is at https://askgina.ai/ai/gina/mcp. SDK and CLI callers
supply an externally acquired Gina bearer token with tools:read; neither client
implements login or OAuth authentication. See
authentication and
Agent Setup to obtain a read-only token.
New here? Start with Start here, which routes you by goal. The Reference below it is for people changing the build, the evals app, or the lint setup.
Start here
Pick your goal
| I want to... | Go to |
|---|---|
| Call Gina from TypeScript code | packages/sdk/README.md |
| Call Gina from a terminal | packages/cli/README.md |
| Use the shared catalog and protocol types | packages/contracts/README.md |
| Install the plugin in a host (Antigravity, Cursor, Grok Bot, Devin, and others) | plugins/ask-gina/README.md |
| Connect ChatGPT, Claude, Codex, or another client | Public Connect guides |
| Run or change the evals | packages/evals/README.md. Start with replay: it makes no network calls and needs no secrets. |
| Work on the public evals app | Public evals app in Reference |
| Contribute a change | ai_docs/contributing.md, then the loop below |
| Edit the public docs site | docs/ is the Mintlify source; authoring rules are in ai_docs/docs/authoring.md |
Antigravity installs local plugin directories with agy plugin install. The
Antigravity connect guide covers
research, Spot, Perps and Predictions, their OAuth scopes, and confirmation for
venue writes. This source-install route does not imply a Marketplace listing.
Contributor loop
You need Bun 1.4.x (the root packageManager is bun@1.4.0). From the
repository root:
bun install --frozen-lockfile
bun run fmt:check
bun run lint
bun run check
bun run test
bun run check:target-conformance
bun run artifacts
bun run verify:artifacts
bun run check:public-boundary
This is the list ai_docs/contributing.md asks you
to run before proposing a change. Pull-request CI runs these and a few more
gates (see What CI runs in Reference). main has no protected
required checks, so CI does not gate merge or publish packages.
Things that surprise people:
- Edit skills in one place. Canonical skill source lives only under
plugins/ask-gina/skills/. Host skill trees are generated at pack time and must not be committed. bun run checkis more than lint. It also runsevals:check-public,evals:check-grading, the TypeScript compiler, and the TypeScript import check.- Docs changes have their own checks. If you touch
docs/ortools/docs/, also runbun run docs:testandbun run docs:check. Releasing a user-facing feature adds the steps inai_docs/release-docs-checklist.md. - Fix Effect diagnostics at the source. Don't suppress them or add
baselines. The one exception is
nodeBuiltinImporton the two synchronous SHA-256 helpers (packages/contracts/src/sha256.tsandpackages/evals/src/canonical-json.ts): EffectCryptois asynchronous, and schema filters and streamed file hashes need a synchronous digest. Importsha256Hexfrom those helpers instead ofnode:crypto.
Map of the repository
| Path | What lives there |
|---|---|
packages/contracts |
@askgina/contracts: public catalog, protocol literals, receipt schemas. |
packages/sdk |
@askgina/sdk: TypeScript client. |
packages/cli |
@askgina/cli: the compiled ask-gina Bun binary. |
packages/evals |
@askgina/evals: replay, live runners, grading, sanitization, public export. |
plugins/ask-gina |
@askgina/plugin-core: canonical plugin inputs (manifest, skills, eval cases, targets) and the Devin install notes. |
apps/evals |
The public evals React/Vite app and its Storybook. Not an npm-published package. |
tools/ |
Build, pack, verify, and boundary-check scripts; eval regrade and public-artifact checks; docs check. |
docs/ |
Public Mintlify docs source. |
ai_docs/ |
Internal engineering docs: contributing, architecture, security, eval handoffs, docs authoring. |
patches/ |
Dependency patches, including the two Storybook docgen compatibility patches. |
scripts/ |
Helper that applies the Effect TSGo patch. |
specs/ |
Design plans. |
Reference
Packages and runtimes
@askgina/contracts: public catalog, protocol literals, and receipt schemas; root-only ESM for Node >=24 and Bun >=1.4@askgina/sdk: TypeScript client; root-only ESM for Node >=24 and Bun >=1.4@askgina/cli: compiled Bunask-ginabinary; Bun 1.4.x only@askgina/plugin-core: host-specific plugin core and loaders, inplugins/ask-gina@askgina/evals: compiled hermetic/live eval tools, shared contracts, adapters, replay, grading, and sanitization; Bun 1.4.x only
The contracts and SDK packages have no CommonJS, browser, edge, or subpath entrypoints.
Commands
Root scripts from package.json, grouped by purpose:
# Setup and quality
bun install --frozen-lockfile
bun run audit
bun run fmt:check
bun run lint
bun run check # quality: evals:check-public, evals:check-grading, vp check, tsc, check:typescript-imports
bun run typecheck
bun run test
bun run check:typescript-imports
bun run check:target-conformance
bun run effect-tsgo:diagnostics
# Packaging and verification
bun run build
bun run artifacts
bun run verify:artifacts
bun run verify:packages
bun run verify:targets
bun run smoke:install
bun run check:public-boundary
bun run check:marketplace:codex
# Public evals app
bun run evals:dev # Vite dev server (default port 5173)
bun run evals:build
bun run evals:typecheck
bun run evals:check-public
bun run evals:check-grading
bun run storybook # Storybook on port 6006
bun run build-storybook
# Evals
bun run eval:replay
bun run eval:responses
bun run eval:codex
bun run eval:openrouter
bun run eval:claude
bun run eval:omp
bun run eval:export-public
# Docs
bun run docs:check
bun run docs:test
What CI runs
Pull-request CI (.github/workflows/ci.yml) runs, in order:
bun install --frozen-lockfile
bun run audit
bun run fmt:check
bun run lint
bun run check
bun run evals:typecheck
bun run evals:build
bun run build-storybook
bun run test
bun run check:target-conformance
bun run artifacts
bun run verify:artifacts
bun run smoke:install
bun run check:public-boundary
It then smokes the Codex marketplace with a pinned Codex CLI at the published
revision. The docs workflow (.github/workflows/docs.yml) runs on pull requests
that touch docs/, tools/docs/, the plugin skills or .mcp.json, or the
contracts entry point: it runs the docs check, skills catalog and sweep comparison
tests (bun run docs:test) and node tools/docs/check.mjs --external.
Public evals app
apps/evals is the public React/Vite app (not an npm-published package) with the Ask Gina
landing-page typography, watercolor artwork, UI components, and Storybook. It has a leaderboard, model
profiles, task evidence explorer, and methodology page. Measured September reports
coexist with explicitly illustrative fixtures. Measured rows cover tool conformance,
not final-answer correctness; public downloads are reviewed projections, not full
conversation archives. The viewer makes no live tool or wallet calls.
CI also runs evals:build and build-storybook. Their outputs stay in
apps/evals/dist/app and apps/evals/dist/storybook, separate from published
package artifacts. Storybook uses the existing TypeScript 7 toolchain plus a
TypeScript 5 compiler-API alias and the two docgen compatibility patches under
patches/. Local fonts and artwork are pinned in tools/public-source-assets.ts.
Before bundling, the public-artifact gate checks historical Claude reports against strict projection fields and an exact reviewed path/hash allowlist. Changed or new Claude JSON requires privacy review and corresponding provenance/allowlist updates; never update a hash merely to admit raw provider output. Full conversations remain outside the public repository. Sanitizing current files does not remove historical Git objects, fork-network copies, or previous deployment/cache contents.
Lint configuration
@shadcn/lint is registered in the root vite.config.ts.
apps/evals/src enables shadcn/no-raw-colors,
shadcn/no-arbitrary-values with allow: ["layout"],
shadcn/no-restyle with allow: ["layout"] plus named evals CSS hooks on
primitives, and shadcn/require-static-classes.
apps/evals/src/components/ui turns no-arbitrary-values, no-restyle, and
require-static-classes off so primitives can keep structural values and
internal variants. bun run lint checks the whole workspace, and
bun run check includes lint. Add further rules under lint.rules, spreading
effectTsgoRecommended.rules first, or in app-scoped lint.overrides. See the
available rules and
configuration examples.
Artifacts
bun run artifacts builds the five package outputs with vp pack; the
custom packer then creates five package tarballs, six complete host archives, one
four-skill candidate archive, and contract, package, target, and eval receipts
under ignored dist/. bun run verify:artifacts performs clean
tarball installs and runtime checks. Nothing here publishes, releases, deploys,
submits, or calls production during pull-request CI.
Eval runners
Live eval runners are bun run eval:responses, eval:codex, eval:openrouter,
eval:claude, and eval:omp; hermetic replay is eval:replay. Credentials,
flags, what each runner can and cannot prove, capture, and publication rules
are in packages/evals/README.md.
One detail the evals README does not name: OpenRouter's --server-url accepts
exactly https://askgina.ai/ai/gina/mcp (the default) or
https://alpha.askgina.ai/ai/gina/mcp. Any other URL, trailing slashes, and
venue MCP endpoints are rejected. OMP native mode's synthetic stored-credential
smoke is not a real OAuth or subscription authentication test.
Ask Gina MCPのよくある質問
Ask Gina MCPをClaude Codeに追加するには
ターミナルでclaude mcp add --transport http plugins https://askgina.ai/ai/gina/mcpを実行します。すべてのプロジェクトで利用するには--scope userを追加します。
Ask Gina MCPをCursorに追加するには
~/.cursor/mcp.jsonを開き、上記のインストールセクションに示すCursor設定を使ってmcpServersの下にサーバーを追加します。
Ask Ginaでの認証方法は?
ユーザーは、tools:read スコープを持つ、外部で取得したGina bearer tokenを提供する必要があります。このサーバー自体では、ログインやOAuthフローの実装は行っていません。