AgentIndex
Search a curated directory of open-source AI agents, MCP servers and AI developer tools.
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": {
"agentindex": {
"url": "https://agentindex.app/api/mcp/"
}
}
}遠端端點
https://agentindex.app/api/mcp/streamable-http它能做什麼
工具清單
工具（5）
🟢search_tools(query, category, limit)
Find AI agents, MCP servers and AI developer tools in the AgentIndex directory by keyword and/or category. Use this when the user describes a need ("MCP server for Postgres", "browser automation agent"); use get_trending instead to browse the best tools without a query. Every keyword must appear (case-insensitive) in the name, description, tags or category. Results are ordered by rank_score, highest first. Returns an array of {id, name, category, description, stars, website, github_url, tags, rank_score}; an empty array means no match, so retry with fewer or broader keywords. Pass an id to get_tool_detail for features, use cases and the install command.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Space-separated keywords, all of which must match, e.g. \"postgres mcp\" or \"browser automation\". Omit to list the top tools of a category."
},
"category": {
"type": "string",
"description": "Exact category name from list_categories (case-insensitive), e.g. \"Browser Automation\" or \"RAG / Knowledge Base\". Omit to search all categories."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10,
"description": "Maximum number of results (1-50, default 10)."
}
}
}輸出結構描述
{
"type": "object",
"properties": {
"tools": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Tool id for get_tool_detail"
},
"name": {
"type": "string"
},
"category": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"stars": {
"type": [
"string",
"number",
"null"
],
"description": "GitHub stars, e.g. \"12.3k\""
},
"website": {
"type": [
"string",
"null"
]
},
"github_url": {
"type": [
"string",
"null"
]
},
"rank_score": {
"type": [
"number",
"null"
],
"description": "AgentIndex rank, 0-100"
},
"tags": {
"type": [
"array",
"null"
],
"items": {
"type": "string"
}
}
},
"required": [
"id",
"name"
]
}
}
},
"required": [
"tools"
]
}🟢get_tool_detail(id)
Get the full AgentIndex record for one tool when you already have its id (from search_tools, get_trending or an AgentIndex URL such as agentindex.app/en/tool/<id>/). Returns name, description, long intro, summary, features, use cases, pros and cons, when to choose or skip it, compatibility, install command, license, stars, last update date, tags, rank_score, website and GitHub URL. Fields that were never filled in are omitted. Returns an isError result if no tool has that id; use search_tools to find the right id.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Tool id exactly as returned by search_tools or get_trending, usually \"<github-owner>-<repo>\", e.g. \"hangwin-mcp-chrome\"."
}
},
"required": [
"id"
]
}輸出結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Tool id for get_tool_detail"
},
"name": {
"type": "string"
},
"category": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"stars": {
"type": [
"string",
"number",
"null"
],
"description": "GitHub stars, e.g. \"12.3k\""
},
"website": {
"type": [
"string",
"null"
]
},
"github_url": {
"type": [
"string",
"null"
]
},
"rank_score": {
"type": [
"number",
"null"
],
"description": "AgentIndex rank, 0-100"
},
"intro_long": {
"description": "Longer introduction"
},
"summary": {
"description": "Short summary, { en, zh } or a string"
},
"features": {
"description": "Feature list"
},
"use_cases": {
"description": "Use case list"
},
"pros": {
"description": "Strengths"
},
"cons": {
"description": "Weaknesses"
},
"choose_if": {
"description": "When to pick this tool"
},
"skip_if": {
"description": "When to pick something else"
},
"compatibility": {
"description": "Compatible clients and platforms"
},
"install_command": {
"type": [
"string",
"null"
]
},
"license": {
"type": [
"string",
"null"
]
},
"last_updated": {
"type": [
"string",
"null"
]
},
"tags": {
"type": [
"array",
"null"
],
"items": {
"type": "string"
}
},
"ai_tags": {
"type": [
"array",
"null"
],
"items": {
"type": "string"
}
}
},
"required": [
"id",
"name"
]
}🟢list_categories
List every category in the AgentIndex directory with the number of tools in it, largest first. Call this before using the category filter of search_tools to get valid names, or to give the user an overview of the directory. Returns an array of {category, count}. Takes no arguments.
輸入結構描述
{
"type": "object",
"properties": {}
}輸出結構描述
{
"type": "object",
"properties": {
"categories": {
"type": "array",
"items": {
"type": "object",
"properties": {
"category": {
"type": "string"
},
"count": {
"type": "integer"
}
},
"required": [
"category",
"count"
]
}
}
},
"required": [
"categories"
]
}🟢get_trending(limit)
Get the highest-ranked tools across the whole AgentIndex directory, for questions like "what are the best/most popular open-source AI tools right now". Ranking is by rank_score (0-100), which combines GitHub stars, how recently the repository was updated and the quality of its documentation; it is not a weekly-growth chart. Use search_tools instead when the user needs a specific kind of tool. Returns an array of {id, name, category, description, stars, rank_score, ai_tags, website, github_url}.
輸入結構描述
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10,
"description": "Number of tools to return (1-50, default 10)."
}
}
}輸出結構描述
{
"type": "object",
"properties": {
"tools": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Tool id for get_tool_detail"
},
"name": {
"type": "string"
},
"category": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"stars": {
"type": [
"string",
"number",
"null"
],
"description": "GitHub stars, e.g. \"12.3k\""
},
"website": {
"type": [
"string",
"null"
]
},
"github_url": {
"type": [
"string",
"null"
]
},
"rank_score": {
"type": [
"number",
"null"
],
"description": "AgentIndex rank, 0-100"
},
"ai_tags": {
"type": [
"array",
"null"
],
"items": {
"type": "string"
}
}
},
"required": [
"id",
"name"
]
}
}
},
"required": [
"tools"
]
}🟡submit_tool(github_url, email)
Suggest a GitHub repository (an AI agent, MCP server or AI developer tool) for listing on AgentIndex. No login or API key needed. The submission is queued for human review, usually within 1-3 days; it does not appear in search results immediately. Tools are listed only if the repository is public and has at least 100 stars. Check with search_tools first that the tool is not already listed. Returns {success, message, github_url}, or an isError result if the URL is not a GitHub repository URL or the submission service is unavailable.
輸入結構描述
{
"type": "object",
"properties": {
"github_url": {
"type": "string",
"pattern": "^https://github\\.com/[^/\\s]+/[^/\\s]+/?$",
"description": "Repository URL in the form https://github.com/<owner>/<repo>, e.g. https://github.com/modelcontextprotocol/servers."
},
"email": {
"type": "string",
"format": "email",
"description": "Optional address that receives an email when the review is done. Only send it if the user provided it."
}
},
"required": [
"github_url"
]
}輸出結構描述
{
"type": "object",
"properties": {
"success": {
"type": "boolean"
},
"message": {
"type": "string"
},
"github_url": {
"type": "string"
}
},
"required": [
"success",
"message"
]
}社群
證據