AgentStatus MCP Index
Live public MCP Index. Search, recommend, and call healthy MCP servers.
我該用這個嗎
品質與安全性
發現項目(2)
- LOW在 get_record 中
- LOW在 compare_records 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": {
"mcp-index": {
"url": "https://index.mcp.agentstatus.dev/mcp"
}
}
}遠端端點
https://index.mcp.agentstatus.dev/mcpstreamable-http它能做什麼
工具清單
工具(6)
🟢search_records(query, section, status, limit, offset, ...)
Search the full public MCP Index. The tools on this connection are only the Index, not the catalog. Pass the job as query. Optional host is cursor, copilot, or vscode. Each match includes a slug and tool names. Run one with call_indexed_tool.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Words an agent would type. Empty returns the directory in stored order.",
"example": "remember me collections"
},
"section": {
"type": "string",
"description": "Section name from list_sections. Partial names match."
},
"status": {
"type": "string",
"description": "Exact facts.status value from this directory: operational, degraded, down, auth_required, unrated.",
"enum": [
"operational",
"degraded",
"down",
"auth_required",
"unrated"
]
},
"limit": {
"type": "integer",
"description": "How many matches to return. Default 20, maximum 50."
},
"offset": {
"type": "integer",
"description": "How many matches to skip."
},
"host": {
"type": "string",
"description": "Optional product host, same as the public Index query: cursor, copilot, vscode."
}
}
}輸出結構描述
{
"type": "object",
"properties": {
"records": {
"type": "array"
},
"total": {
"type": "integer"
},
"offset": {
"type": "integer"
},
"limit": {
"type": "integer"
}
}
}🟢get_record(id)
Look up one directory item by id, slug, or exact name.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Record id, slug, or exact title.",
"example": "ipnex"
}
},
"required": [
"id"
]
}輸出結構描述
{
"type": "object",
"properties": {
"record": {
"type": "object"
}
}
}🟢recommend_records(need, section, status, host, limit)
Return public MCP servers from the full Index for a need. Each match includes a slug and tool names. This tool only reads the Index.
輸入結構描述
{
"type": "object",
"properties": {
"need": {
"type": "string",
"description": "What the agent is looking for.",
"example": "remember me collections"
},
"section": {
"type": "string",
"description": "Optional section or partial section name."
},
"status": {
"type": "string",
"description": "Exact facts.status value from this directory: operational, degraded, down, auth_required, unrated.",
"enum": [
"operational",
"degraded",
"down",
"auth_required",
"unrated"
]
},
"host": {
"type": "string",
"description": "Optional product host, same as search_records: cursor, copilot, vscode."
},
"limit": {
"type": "integer",
"description": "How many recommendations to return. Default 5, maximum 10."
}
},
"required": [
"need"
]
}輸出結構描述
{
"type": "object",
"properties": {
"records": {
"type": "array"
},
"recommendations": {
"type": "array"
},
"total": {
"type": "integer"
},
"criteria": {
"type": "object"
}
}
}🟢compare_records(records)
Compare two to five directory items by id, slug, or exact name. Returns stored details and the fields that differ.
輸入結構描述
{
"type": "object",
"properties": {
"records": {
"type": "array",
"items": {
"type": "string"
},
"minItems": 2,
"maxItems": 5,
"description": "Two to five record ids, slugs, or exact titles.",
"example": [
"ipnex",
"remember-me-collections"
]
}
},
"required": [
"records"
]
}輸出結構描述
{
"type": "object",
"properties": {
"records": {
"type": "array"
},
"differences": {
"type": "array"
},
"missing": {
"type": "array"
}
}
}🟢list_sections
Show the sections in MCP for AgentStatus MCP Index.
輸入結構描述
{
"type": "object",
"properties": {}
}輸出結構描述
{
"type": "object",
"properties": {
"sections": {
"type": "array"
}
}
}🟢call_indexed_tool(slug, tool, arguments)
Run a tool on a public MCP server from the full AgentStatus Index. This connection does not list those servers. Call search_records or recommend_records first, then pass that slug and tool. The call is sent to that server and its result is returned here.
輸入結構描述
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Index slug, such as trip-logistics."
},
"tool": {
"type": "string",
"description": "Tool name on that server."
},
"arguments": {
"type": "object",
"description": "Arguments for that tool.",
"additionalProperties": true
}
},
"required": [
"slug",
"tool"
]
}輸出結構描述
{
"type": "object"
}社群
證據