anteroom

Frontier-AI vendor commitments, safety framework history, corpus, and partnership patterns.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
100%
命名质量
100%
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

~829token 数(工具定义)
~1.3 KB典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.65%)

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": {
    "anteroom": {
      "url": "https://mcp.anteroom.so/mcp"
    }
  }
}

远程端点

https://mcp.anteroom.so/mcpstreamable-http

它能做什么

工具清单

工具(5)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_vendor_commitments(vendor_slug)

Get the seven tracked commercial commitments (AUP, no-train default, output ownership, IP indemnity program, retention default, deprecation notice, safety framework version) for a frontier AI vendor. Each commitment carries the quoted primary-source text, source URL, and effective date.

输入模式

{
  "type": "object",
  "properties": {
    "vendor_slug": {
      "type": "string",
      "description": "Vendor slug. One of: anthropic, openai, google-vertex, meta, xai."
    }
  },
  "required": [
    "vendor_slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_framework_version_history(lab_slug)

Get the full version ledger of a frontier AI lab's safety framework (Responsible Scaling Policy, Preparedness Framework, Frontier Safety Framework, or equivalent). Returns every published version, effective date, published changelog, and primary source URL.

输入模式

{
  "type": "object",
  "properties": {
    "lab_slug": {
      "type": "string",
      "description": "Lab slug. One of: anthropic, openai, google-deepmind, meta, xai."
    }
  },
  "required": [
    "lab_slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢search_corpus(query, jurisdiction, lens, limit)

Search Anteroom's tracked corpus of AI-relevant regulatory provisions across jurisdictions (EU AI Act, US state laws, sectoral rules, international frameworks) and legal lenses. Returns matching provisions with primary-source URLs and confidence tags.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 2,
      "description": "Free-text search query. Matched against provision label, plain-language summary, and primary-source excerpt."
    },
    "jurisdiction": {
      "type": "string",
      "description": "Optional jurisdiction filter. Examples: eu-ai-act, colorado-sb26-189, illinois-hb-3773, china-generative-ai-measures, uk-ai-safety-institute, singapore-model-ai-framework."
    },
    "lens": {
      "type": "string",
      "description": "Optional legal-lens filter. One of: ai-specific, privacy, sectoral, employment, accessibility, consumer-protection, ip, security, export-control, liability."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 15,
      "description": "Max number of provisions to return. Default 15, max 50."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_partnership_pattern(pattern_slug)

Get a named strategic AI partnership pattern with its plain-language description, example clauses, kill-list moves, scholarly anchors, and real-world precedent anchors.

输入模式

{
  "type": "object",
  "properties": {
    "pattern_slug": {
      "type": "string",
      "description": "Pattern slug. Examples: compute-backed-strategic-invest, hyperscaler-exclusive-then-multi-home, oem-with-third-party-ai-model, capacity-reserve-agreement, compute-for-equity, sole-source-ip-grant, sovereign-trade-capacity, white-label-metered."
    }
  },
  "required": [
    "pattern_slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_partnerships_by_pattern(pattern_slug, limit)

List every tracked public AI strategic partnership that Anteroom has classified as an instance of a given pattern. Returns partnership metadata with permalink to the primary-source-anchored deal page.

输入模式

{
  "type": "object",
  "properties": {
    "pattern_slug": {
      "type": "string",
      "description": "Pattern slug. See get_partnership_pattern for the list."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 20,
      "description": "Max number of partnerships to return. Default 20, max 50."
    }
  },
  "required": [
    "pattern_slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

推荐提示词

search_research
Search for information about [topic] using anteroom
预期工具: search_corpus
find_specific
Find [specific item] using anteroom
预期工具: search_corpus
retrieve_data
Get details about [item] from anteroom
预期工具: get_vendor_commitments
fetch_info
Fetch [information type] using anteroom
预期工具: get_vendor_commitments
research_workflow
Search for [topic], then get detailed information about the top results using anteroom
预期工具: search_corpusget_vendor_commitments

社区

评价此服务器

证据

最近观测

已验证未记录版本5 个工具
已验证未记录版本5 个工具