MCP Rating
Search MCP servers, with our own start-test results, required keys, tools and token cost.
我該用這個嗎
品質與安全性
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": {
"search": {
"url": "https://mcprating.io/mcp/"
}
}
}遠端端點
https://mcprating.io/mcp/streamable-httphttps://mcprating.io/mcp/ssesse它能做什麼
工具清單
工具（6）
🟢search_servers(query, category, sortBy, limit)
Search the MCP Rating index of MCP servers. Returns matches for a query, optionally filtered by category and sorted by quality, stars, downloads, recency, or name, each marked with the outcome of our own start test when we have run one. Quality scores are algorithmic estimates.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"description": "Search query to match against server names",
"type": "string"
},
"category": {
"description": "Category slug to filter by (e.g. 'developer-tools')",
"type": "string"
},
"sortBy": {
"description": "Sort order",
"type": "string",
"enum": [
"quality",
"stars",
"downloads",
"recent",
"name"
]
},
"limit": {
"description": "Max results (default 20)",
"type": "number",
"minimum": 1,
"maximum": 50
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_server(slug)
Get what is known about one MCP server by slug: whether it started when we ran it ourselves (no credentials, on a schedule), how to run it (install command or hosted endpoint), the keys it declares, its tools with their parameters, and roughly how many tokens its tool definitions cost. Listings are informational — verify details before installing.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "The server's unique slug identifier"
}
},
"required": [
"slug"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_categories
List all available MCP server categories with the count of servers in each.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_index_stats
Get overall statistics about the MCP Rating index: total servers, top categories, and last crawl time.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡get_install_config(slug, client)
Generate a ready-to-paste configuration snippet for connecting a discovered MCP server to Claude Desktop or Cursor. MCP servers cannot auto-install — users must manually add configuration. This tool reduces that friction.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "The server's unique slug identifier"
},
"client": {
"description": "Target client (default: claude_desktop). 'generic' returns a transport-neutral {command,args,env} object; 'surge' returns the Surge install shape.",
"type": "string",
"enum": [
"claude_desktop",
"cursor",
"surge",
"generic"
]
}
},
"required": [
"slug"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢discover_server(slug)
Fetch the live .well-known/mcp discovery manifest from an indexed MCP server. Returns transport endpoints, capabilities, and auth requirements needed to connect. Only works for servers that support MCP discovery.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "The server's unique slug identifier"
}
},
"required": [
"slug"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據