Magist

io.github.magist-io由 GitHub 帳號 magist-io 發布v0.1.1更新於 Nov 6, 2026

Deterministic, cited regulatory research for product launches; legal information, not legal advice.

已驗證Streamable HTTP可網頁執行安全與監控商業與電商

概覽

AI 產生的概覽

Magist 為助理提供可重現、附引用的法規研究:產品可能適用的法律、相應控制措施、執法案例與律師資源。

可以做什麼
  • 依關鍵字或編號搜尋與查閱法規,含引用、司法管轄區、狀態與複核日期
  • 對產品功能、目標市場與受眾執行確定性合規引擎,回傳觸發的法規、控制措施、複雜度等級與阻擋項目
  • 查詢某法規對應的控制措施,以及可落實某控制措施的廠商或自建方案
  • 取得近期執法行動,含罰款、主管機關與一手來源連結
  • 依司法管轄區與執業領域搜尋公開律師名錄
  • 列出有效的功能與市場識別碼,並驗證簽章的依據證明權杖
適用情境
適合在產品上市或功能規劃前研究可能適用的法規、把義務對應到控制措施,或在諮詢律師前蒐集執法案例與候選律師。它提供的是供研究與轉交律師使用的法律資訊,並非法律意見。
執行需求
可使用遠端 Streamable-HTTP 端點(免安裝),或以 npx 執行 npm 橋接套件,後者需要 Node.js 18 以上版本。不需驗證、API 金鑰或標頭。可透過環境變數 MAGIST_MCP_URL 指向其他部署。需要網路連線。
安裝前請注意
存取不需驗證且受速率限制,工具呼叫遙測可能被記錄。compute_requirements 會產生保留最多 90 天的公開回執報告連結,因此只應送出非機密的公開或合成輸入,避免個人、機密或受保密特權保護的資訊。語料庫仍在測試階段,部分條目由 AI 產生、尚待律師複核,輸出不構成法律意見。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Magist,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.magist-io%2Fmagist/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "magist": {
      "type": "http",
      "url": "https://magist.io/api/mcp"
    }
  }
}

README

@magist/mcp-server

Connect Magist to your AI host over the Model Context Protocol. Magist is an open, deterministic, cited reference for product regulation: which laws apply to a product, the obligations and Controls they imply, and the primary sources behind each. Open data (CC BY-SA 4.0), a deterministic engine (same inputs produce the same outputs, no LLM in the path), permanent citation URLs, and a named-practitioner attribution on every response.

This package is a thin stdio bridge to the hosted server at https://magist.io/api/mcp. Remote-capable hosts can skip it and point straight at that URL.

Offline receipt integrity

The separate receipt-v9 content-integrity utility checks a saved JSON body hash using only Node built-ins. It makes no network call and does not run the engine or authenticate the sender. Its synthetic tests and source are separate from the published bridge and plugin payloads.

Research plugin packages (experimental previews)

This repository also contains the separate magist-research 0.1.1 portable plugin: root plugin.json, the remote connection in mcp.json, and a newly authored workflow in skills/magist-research/. It connects directly to the public HTTPS service and does not run the npm stdio bridge.

The portable connection uses only type and url, as allowed by the Agent Plugins 1.0.0 MCP schema. The endpoint requires no authentication. The schema does not admit the server-level authentication extensions shown in some host-specific examples; those extensions are omitted here. Schema validation alone does not establish that a host can install and run the complete plugin.

Create its bounded source package with Python 3.9 or newer:

bash
python3 scripts/package-plugin.py --output /absolute/new/path/magist-research-0.1.1.zip

The ZIP includes the two portable manifests, the skill and its MCP dependency declaration, an existing public Magist icon, and this repository's MIT license. It excludes the bridge executable, dependencies, private platform source and assets. The plugin version is independent of @magist/[email protected].

This is a proposed integration package, not an accepted directory listing or a host validation certificate. Public submission uses OpenAI's With MCP route; publisher verification, actual host/reviewer cases, media, any required visual assets, connection checks and submission review remain separate requirements. See the portable package format.

OpenAI listing metadata and five positive/three negative reviewer scenarios are included in plugin.json. Those are proposed host cases, not records of completed installed-plugin runs. A reviewer video is not yet supplied; the website demo is not an installed-plugin walkthrough.

Claude plugin and optional Desktop bundle

The Claude plugin lives at integrations/claude. It uses Claude's separate .claude-plugin/plugin.json and .mcp.json format, pins its reviewed Claude skill bytes, and connects to the same hosted endpoint. Version 0.1.2 adds an explicit audience, bounded research work shape, evidence-confidence bands and escalation rules, retaining the illustrative lookup and response template. These design controls do not establish unconditional framework readiness, installed-host behavior or directory acceptance. The shared OpenAI skill and optional Desktop bundle remain separate, unchanged artifacts. Its clean subfolder excludes this repository's top-level bin/, which chat and Cowork do not accept in a plugin. Build both artifacts without installing dependencies:

bash
python3 scripts/package-claude.py --kind plugin --output /absolute/new/path/magist-claude-plugin-0.1.2.zippython3 scripts/package-claude.py --kind desktop --output /absolute/new/path/magist-desktop-0.1.1.mcpb

The .mcpb embeds the exact dependency-free published 0.1.1 bridge and requires Node.js 18 or newer. It is unsigned and for private Desktop testing. Claude's current directory no longer accepts Desktop MCPB listings. For public review, submit the remote MCP connector and the integrations/claude plugin folder as two linked submissions from the same intended publisher organization. See Claude's current directory routes. No package here implies installation, portal validation, acceptance or a completed Claude workflow.

Beta: content under attorney review. The server is live and the engine is stable; substantive attorney review of the regulation corpus is in progress. Entries carry a contentReviewStatus field (reviewed is human-verified, draft is AI-prepared and pending review). Magist returns legal information for research and attorney handoff, not legal advice. Consult a licensed attorney before relying on any output for a launch decision.

One-line install

Claude Code (CLI) uses the remote transport directly (no npm install):

bash
claude mcp add --transport http magist https://magist.io/api/mcp

Claude Desktop / Cursor / Windsurf (npx): add the bridge to the host's mcpServers config:

json
{  "mcpServers": {    "magist": {      "command": "npx",      "args": ["-y", "@magist/mcp-server"]    }  }}
  • Claude Desktop: Settings -> Developer -> Edit Config (claude_desktop_config.json). Restart Claude after saving.

  • Cursor: Settings -> MCP -> Add new server, or edit ~/.cursor/mcp.json.

  • Windsurf: edit ~/.codeium/windsurf/mcp_config.json, then reload.

  • Codex: add to ~/.codex/config.toml:

    toml
    [mcp_servers.magist]command = "npx"args = ["-y", "@magist/mcp-server"]

ChatGPT (Developer Mode / Connectors), Manus, and other remote-capable hosts: add a custom connector pointing at the Streamable-HTTP endpoint https://magist.io/api/mcp (no npm package needed).

Verify it works

A 200 with name: "magist" means the endpoint is live:

bash
curl -s https://magist.io/api/mcp

List the tools (you should see nine):

bash
curl -s -X POST https://magist.io/api/mcp \  -H 'content-type: application/json' \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

In your host, once connected, ask Magist to look up COPPA and list its Controls. A working connection returns a cited regulation record, not a refusal or a no-such-tool error.

Tools

ToolWhat it returns
lookup_regulation(id)One regulation's structured record: citation, jurisdiction, status, review dates, plain-language summary, and the Controls that may satisfy it.
search_regulations(query, filters?)Deterministic keyword + filter search over the corpus, with permanent citation URLs.
compute_requirements(features, markets, audiences, businessModel?)Runs the deterministic engine: triggered regulations + Controls, complexity tier, blocker count, per-audience breakdown. Creates or refreshes an idempotent public receipt-report link retained for up to 90 days; use only nonconfidential public or synthetic inputs.
find_controls(regulationId)Controls that may satisfy a regulation, each with a priority signal and summary.
find_vendors(controlId, jurisdiction?)Vendors and in-house approaches that implement a Control, with effort/cost and a source disclosure. Magist does not accept payment from vendors.
get_enforcement(regulationId?, since?, limit?)Recent enforcement actions with penalties, authorities, and primary-source links.
find_counsel(jurisdiction, practiceArea?, language?)Open counsel directory by jurisdiction and practice area. Inclusion is not endorsement.
list_feature_catalog()The closed feature, market, and audience identifiers accepted by compute_requirements, so agents can validate inputs before analysis.
verify_ai_answer(token)Verifies a signed Magist grounding-proof token from the REST API. It proves what Magist served, not legal correctness or applicability.

Eight tools read the public corpus or verify a grounding-proof signature. compute_requirements additionally persists the public receipt report described above. Access is unauthenticated and subject to server rate limits; do not send personal, confidential or privileged information. Tool-call telemetry may be recorded. The bridge package license does not license the hosted platform.

Self-hosting

Set MAGIST_MCP_URL to point the bridge at your own deployment of the open corpus and engine:

json
{  "mcpServers": {    "magist": {      "command": "npx",      "args": ["-y", "@magist/mcp-server"],      "env": { "MAGIST_MCP_URL": "https://your-host.example.com/api/mcp" }    }  }}

For host LLM developers

Every tool response is wrapped in a canonical envelope. When you render a Magist response to a user: render the disclaimer.text field verbatim; do not restate outputs as directives or conclusions; surface the practitioner attribution and the verification field; suggest a licensed attorney when counsel_recommended is true; and prefer the citations links when you summarize.

Links

來源:README.md,提交 2912d9f

工具

9

lookup_regulation

Look up a regulation

Look up one regulation by its Magist id and return structured research information: title, citation, jurisdiction, status, review dates, a plain-language summary, and the Controls that may satisfy it. Returns facts about what a regulation says, not a determination of how it applies to a specific product. Consult counsel for situation-specific questions.

輸入參數id必填

search_regulations

Search regulations

Search Magist’s regulation corpus by keyword with optional filters (jurisdiction, domain, status, content-review status, coverage depth). Returns a paginated list of matching regulations with permanent citation URLs. Deterministic: the same query and filters return the same results every time. Returns research information for discovery, not a determination of which regulations apply to a specific product.

輸入參數limitquerydomainoffsetstatusjurisdictioncoverageDepthcontentReviewStatus

compute_requirements

Compute regulatory requirements

Run Magist’s deterministic compliance engine over a product description (features, target markets, audience age bands, optional business model) and return the regulations and Controls that may be triggered, a complexity tier with a numeric score, a blocker count, and a per-audience cohort breakdown. The call also creates or refreshes an idempotent public report URL for the receipt, retained for up to 90 days. Deterministic and reproducible: the same inputs always produce the same output, with no LLM in the path. Returns which obligations may apply for research purposes; it is not a determination that they do apply, and does not replace counsel. Consult a licensed attorney before relying on the result.

輸入參數markets必填features必填audiencesbusinessModel

find_controls

Find compliance controls

Given a regulation id, return the compliance Controls that may satisfy it, each with a priority signal (blocker / required / evaluate / best-practice) and a short summary of the work involved. Returns research information about typical control mappings, not a determination that a given product needs them. Consult counsel for scoping.

輸入參數regulationId必填

find_vendors

Find implementation vendors

Given a Control id, list third-party vendors and in-house approaches that may implement it, with effort/cost signals and a source-disclosure (editorial research vs vendor submission). Magist does not accept payment from vendors and does not rank or endorse them. Returns a neutral catalog for research; evaluate fit independently.

輸入參數controlId必填jurisdiction

get_enforcement

Get enforcement actions

Return recent regulatory enforcement actions from Magist’s catalog, optionally filtered by regulation id and a since-date. Each action includes the penalty, authority, a primary-source link, and (where authored) a practitionerAnalysis: a hedged, third-person editorial note on what the action illustrates, informational context that never addresses a specific product. penaltyAmount is null when no monetary amount is recorded (pending, confidential, annulled, or non-monetary outcomes; the amount string carries the honest description). Returns historical facts about what regulators have done: informational context, not a prediction about a specific product.

輸入參數limitsinceregulationId

find_counsel

Find licensed counsel

Search Magist’s open counsel directory for law firms by jurisdiction and practice area. Returns an editorial / firm-claimed directory to help a user identify licensed attorneys to consult. Inclusion is not endorsement; verify bar status and conflicts independently before engaging.

輸入參數languagejurisdiction必填practiceArea

verify_ai_answer

Verify a Magist citation

Verify a Magist grounding-proof token: the "groundingProof" field on a regulation or control record from the REST API (GET /api/v1/regulations/{id} or /api/v1/controls/{id}) when the server has signing enabled. MCP tool responses do not carry these tokens. Proves the citation was genuinely served by Magist's server for that exact atom at that exact corpus version; it does NOT verify legal correctness or that any obligation applies to a product. Returns valid:false with a reason when the token is missing, malformed, unsigned, or fails signature verification; this is expected when the record never carried a token (signing is an opt-in server setting).

輸入參數token必填

list_feature_catalog

List supported features and markets

Return Magist’s closed catalogs of valid product feature ids and target market ids, each with a short human-readable label -- the exact identifiers compute_requirements accepts as "features" and "markets". Use this to validate ids before calling compute_requirements; ids outside these catalogs are rejected with an actionable error. Deterministic and reproducible; this is reference data, not itself a regulatory determination.

無需輸入參數。

版本歷史

1
  1. v0.1.1最新Oct 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分