MRX Public MCP
Read-only, source-linked mineral-rights education from MineralRightsXchange.com.
我该使用它吗
质量与安全性
发现（2）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 mrx_read_page 中
基于对工具定义和协议合规性的自动分析。
上下文开销
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": {
"mrx-mcp": {
"url": "https://mrx-public-mcp.vercel.app/mcp"
}
}
}远程端点
https://mrx-public-mcp.vercel.app/mcpstreamable-http它能做什么
工具清单
工具（8）
🟢mrx_status
Check the current public sitemap/manifest, server capabilities and boundaries.
输入模式
{
"type": "object",
"properties": {},
"title": "mrx_statusArguments"
}🟢mrx_search_guides(query, limit, jurisdiction, topic)
Search verified public MRX titles, headings and article text. Optional jurisdiction/topic filters are source-text matches, not legal conclusions. Coverage reports omissions. Do not include personal data in a research query.
输入模式
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"limit": {
"default": 8,
"title": "Limit",
"type": "integer"
},
"jurisdiction": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Jurisdiction"
},
"topic": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Topic"
}
},
"required": [
"query"
],
"title": "mrx_search_guidesArguments"
}🟢search(query)
Search public MRX educational guides. Returns citable canonical document IDs. No private cases. Fetch each source before relying on it. An incomplete index produces an error rather than an apparently exhaustive compatibility response.
输入模式
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
}
},
"required": [
"query"
],
"title": "searchArguments"
}输出模式
{
"type": "object",
"properties": {
"results": {
"items": {
"$ref": "#/$defs/SearchItem"
},
"title": "Results",
"type": "array"
}
},
"required": [
"results"
],
"$defs": {
"SearchItem": {
"properties": {
"id": {
"title": "Id",
"type": "string"
},
"title": {
"title": "Title",
"type": "string"
},
"url": {
"title": "Url",
"type": "string"
}
},
"required": [
"id",
"title",
"url"
],
"title": "SearchItem",
"type": "object"
}
},
"title": "SearchOutput"
}🟢fetch(id)
Fetch a verified public document by the canonical URL ID returned by search. Return source text, attribution and dates when available; never infer a review.
输入模式
{
"type": "object",
"properties": {
"id": {
"title": "Id",
"type": "string"
}
},
"required": [
"id"
],
"title": "fetchArguments"
}输出模式
{
"type": "object",
"properties": {
"id": {
"title": "Id",
"type": "string"
},
"title": {
"title": "Title",
"type": "string"
},
"text": {
"title": "Text",
"type": "string"
},
"url": {
"title": "Url",
"type": "string"
},
"metadata": {
"additionalProperties": true,
"title": "Metadata",
"type": "object"
}
},
"required": [
"id",
"title",
"text",
"url"
],
"title": "FetchOutput"
}🟢mrx_read_page(url)
Read one canonical public MRX page after sitemap, hash and indexability checks. Accepts only https://mineralrightsxchange.com/ URLs returned by search. Private routes, off-site URLs, queries, fragments and redirects are rejected.
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
}
},
"required": [
"url"
],
"title": "mrx_read_pageArguments"
}🟢mrx_get_started
Read MRX's current public homepage and its source-linked next-step links. This does not submit a request, create a case, or perform a human review.
输入模式
{
"type": "object",
"properties": {},
"title": "mrx_get_startedArguments"
}🟢mrx_website_capabilities(section)
Read current website capabilities from verified public sources. Sections: overview, ai_guides, investors (Graham), human_review. Returns website descriptions, not access to chat, bookings, uploads or private cases.
输入模式
{
"type": "object",
"properties": {
"section": {
"default": "overview",
"title": "Section",
"type": "string"
}
},
"title": "mrx_website_capabilitiesArguments"
}🟢mrx_list_public_pages(category, offset, limit, content_revision)
Discover current public pages, including website journeys and AI guide profiles. Categories: all, articles (blog paths), ai_guides, website. Pass content_revision on subsequent pages to detect a changing inventory. Read a page before citing it.
输入模式
{
"type": "object",
"properties": {
"category": {
"default": "all",
"title": "Category",
"type": "string"
},
"offset": {
"default": 0,
"title": "Offset",
"type": "integer"
},
"limit": {
"default": 50,
"title": "Limit",
"type": "integer"
},
"content_revision": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Content Revision"
}
},
"title": "mrx_list_public_pagesArguments"
}社区
证据