Magist

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

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
90%
命名质量
98%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~2,352token 数(工具定义)
~1.6 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 1.84%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "magist": {
      "command": "npx",
      "args": [
        "@magist/mcp-server"
      ]
    }
  }
}

可运行的软件包

npm@magist/mcp-server0.1.1stdio

远程端点

https://magist.io/api/mcpstreamable-http

它能做什么

工具清单

工具(9)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢lookup_regulation(id)

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.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100,
      "pattern": "^[a-z0-9][a-z0-9-]*$",
      "description": "Magist regulation id, e.g. \"gdpr\", \"coppa\", \"ai-act\". Use search_regulations to discover ids."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢search_regulations(query, jurisdiction, domain, status, contentReviewStatus, ...)

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.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 300,
      "description": "Free-text keywords. Optional; omit to browse with filters only."
    },
    "jurisdiction": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 40
      },
      "maxItems": 20,
      "description": "Jurisdiction codes/names, e.g. [\"EU\",\"US\"]."
    },
    "domain": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 60
      },
      "maxItems": 20,
      "description": "Compliance domain ids, e.g. [\"data-privacy\",\"age-verification\"]."
    },
    "status": {
      "type": "string",
      "maxLength": 40,
      "description": "Lifecycle status filter, e.g. \"active\", \"proposed\"."
    },
    "contentReviewStatus": {
      "type": "string",
      "enum": [
        "reviewed",
        "draft"
      ],
      "description": "Filter by practitioner-review state."
    },
    "coverageDepth": {
      "type": "string",
      "enum": [
        "deep",
        "standard",
        "thin"
      ],
      "description": "Filter by editorial coverage depth."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "description": "Page size (default 10, max 25)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10000,
      "description": "Pagination offset (default 0)."
    }
  },
  "additionalProperties": false
}
🟢compute_requirements(features, markets, audiences, businessModel)

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.

输入模式

{
  "type": "object",
  "properties": {
    "features": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 80
      },
      "minItems": 1,
      "maxItems": 100,
      "description": "Product feature ids from the closed catalog, e.g. [\"account-creation\",\"text-chat\",\"iap\",\"ai-content-gen\"]. Call list_feature_catalog for the full set of valid ids; an id outside the catalog is rejected with an actionable error."
    },
    "markets": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 40,
        "pattern": "^[a-z0-9][a-z0-9-]*$"
      },
      "minItems": 1,
      "maxItems": 160,
      "description": "Target market codes, e.g. [\"eu\",\"us\",\"california\",\"uk\"]. Call list_feature_catalog for the full set of valid ids; an id outside the catalog is rejected with an actionable error."
    },
    "audiences": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "under13",
          "14-17",
          "18-plus"
        ]
      },
      "maxItems": 3,
      "description": "Audience age bands. Exactly these three ids exist."
    },
    "businessModel": {
      "type": "object",
      "additionalProperties": true,
      "description": "Optional business-model context (role, participants, transactionInvolvement, dataHandling). Validated server-side via the same allowlist as /api/compute-requirements."
    }
  },
  "required": [
    "features",
    "markets"
  ],
  "additionalProperties": false
}
🟢find_controls(regulationId)

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.

输入模式

{
  "type": "object",
  "properties": {
    "regulationId": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100,
      "pattern": "^[a-z0-9][a-z0-9-]*$",
      "description": "Magist regulation id, e.g. \"coppa\"."
    }
  },
  "required": [
    "regulationId"
  ],
  "additionalProperties": false
}
🟢find_vendors(controlId, jurisdiction)

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.

输入模式

{
  "type": "object",
  "properties": {
    "controlId": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100,
      "pattern": "^[a-z][a-z0-9-]*$",
      "description": "Magist Control id, e.g. \"age-verification-process\"."
    },
    "jurisdiction": {
      "type": "string",
      "maxLength": 40,
      "description": "Optional market/region filter, e.g. \"eu\". Applied only when a vendor declares supported regions."
    }
  },
  "required": [
    "controlId"
  ],
  "additionalProperties": false
}
🟢get_enforcement(regulationId, since, limit)

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.

输入模式

{
  "type": "object",
  "properties": {
    "regulationId": {
      "type": "string",
      "maxLength": 100,
      "pattern": "^[a-z0-9][a-z0-9-]*$",
      "description": "Filter to actions related to this regulation id."
    },
    "since": {
      "type": "string",
      "maxLength": 10,
      "description": "ISO date (YYYY-MM-DD) or year (YYYY). Returns actions on or after this date."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "description": "Max actions to return (default 10, max 50)."
    }
  },
  "additionalProperties": false
}
🟢find_counsel(jurisdiction, practiceArea, language)

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.

输入模式

{
  "type": "object",
  "properties": {
    "jurisdiction": {
      "type": "string",
      "minLength": 1,
      "maxLength": 40,
      "description": "Jurisdiction code, e.g. \"us\", \"us-ca\", \"eu\", \"uk\". A country/region name (\"Australia\", \"United States\") is also accepted and resolved to its code; the code actually searched comes back as `resolvedJurisdiction`. A code matches itself and its sub-jurisdictions, never the reverse — a firm listed only for \"us\" is not returned for \"us-mt\"."
    },
    "practiceArea": {
      "type": "string",
      "maxLength": 60,
      "description": "Optional practice-area / compliance-domain id, e.g. \"data-privacy\", \"age-verification\"."
    },
    "language": {
      "type": "string",
      "maxLength": 40,
      "description": "Optional preferred language. Accepted for forward-compatibility; not yet a filter at launch."
    }
  },
  "required": [
    "jurisdiction"
  ],
  "additionalProperties": false
}
🟢verify_ai_answer(token)

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).

输入模式

{
  "type": "object",
  "properties": {
    "token": {
      "type": "object",
      "description": "The groundingProof object exactly as received on a prior response (carries alg, mgstId, corpusVersion, quoteHash, nonce, and the signature fields). Pass it back unmodified."
    }
  },
  "required": [
    "token"
  ],
  "additionalProperties": false
}
🟢list_feature_catalog

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.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本9 个工具