Machine Relations Index
Which source domains AI answer engines cite, by buyer category and question shape.
我該用這個嗎
品質與安全性
發現項目（1）
- LOWTool 'mri_get_domain' description lacks action verb在 mri_get_domain 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"mri": {
"url": "https://machinerelations.ai/mcp"
}
}
}遠端端點
https://machinerelations.ai/mcpstreamable-http它能做什麼
工具清單
工具（4）
🟢mri_list_categories
List every Machine Relations Index category (e.g. cybersecurity, fintech, enterprise-software, ai-visibility-geo) with the question shapes that have published citation rates, plus the source-role vocabulary. Call this first to get a valid category key.
輸入結構描述
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢mri_get_category(category)
Return one category's question shapes (best tools, how buyers choose, comparisons, top lists, problem-first research, is it worth it, news) and the evidence state of each: published with rates, collecting, or not collectable.
輸入結構描述
{
"type": "object",
"properties": {
"category": {
"type": "string",
"description": "Category key from mri_list_categories, e.g. cybersecurity."
}
},
"required": [
"category"
],
"additionalProperties": false
}🟢mri_get_cited_sources(category, question_shape, source_role, limit, offset)
Ranked source domains that AI answer engines cite for one category and question shape, with citation rate (share of monitored answer runs citing the domain), rank, percentile and source role (editorial publication, vendor-owned, analyst research, community, academic/government, market database, wire distribution). Use to answer 'which publications/sources does ChatGPT or Perplexity cite for <category>' or 'where should a <category> brand earn coverage to be cited by AI'.
輸入結構描述
{
"type": "object",
"properties": {
"category": {
"type": "string",
"description": "Category key, e.g. cybersecurity."
},
"question_shape": {
"type": "string",
"enum": [
"best_x",
"how_choose",
"is_x_worth",
"news_topic",
"problem_first",
"top_list",
"x_vs_y"
],
"description": "Buyer question pattern: best_x (best X tools), how_choose (how to choose), is_x_worth (is it worth it), news_topic (recent news), problem_first (how to solve a problem), top_list (top platforms), x_vs_y (A vs B)."
},
"source_role": {
"type": "string",
"description": "Optional filter, e.g. editorial_media for publications only, vendor_owned, analyst_research, community_social."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 25
},
"offset": {
"type": "integer",
"minimum": 0,
"default": 0
}
},
"required": [
"category",
"question_shape"
],
"additionalProperties": false
}🟢mri_get_domain(domain)
For one domain or URL, return how often AI answer engines cite it: overall citation rate, which engines cite it, confidence tier, rank among all cited domains and within its source role, and per-category segment rates. Use to answer 'does ChatGPT/Perplexity cite <site>' or 'how authoritative is <publication> as an AI source'.
輸入結構描述
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "A domain (techcrunch.com) or any URL on it."
}
},
"required": [
"domain"
],
"additionalProperties": false
}社群
證據