AI Agent Marketplace Index MCP Server

What is AI Agent Marketplace Index MCP Server about?

The server enables AI assistants and developers to search the AI Agent Marketplace Index by free‑text queries or predefined categories (e.g., coding agents, GUI agents, mobile agents). It also aggregates performance metrics such as search rankings, GitHub stars, and arXiv citations, and offers an API for publishing agents to the marketplace.

How to use AI Agent Marketplace Index MCP Server?

1. Installation

   git clone https://github.com/AI-Agent-Hub/ai-agent-marketplace-index-mcp.git
   cd ai-agent-marketplace-index-mcp
   uv venv
   source .venv/bin/activate   # Windows: .venv\Scripts\activate
   uv pip install -e .
   

2. Run the server

   uv run -m ai-agent-marketplace-index-mcp
   

3. Configure a compatible MCP client (e.g., Claude Desktop) by adding the command and arguments to the client’s configuration JSON as shown in the README.
4. Invoke tools – call search_ai_agent(q, limit, timeout) from your LLM workflow or make HTTP requests to the exposed endpoints.

Key Features of AI Agent Marketplace Index MCP Server

• Search by query or category – retrieve agents matching keywords or specific domains.
• Performance monitoring – collect Google/Bing ranking, GitHub stars, and arXiv references for each agent.
• Marketplace API – list new agents, update metadata, and integrate with other MCP servers.
• Comprehensive error handling – graceful degradation for missing data or API failures.
• MCP compatibility – works with Claude Desktop, Cursor, and any MCP‑compatible client.

Use Cases of AI Agent Marketplace Index MCP Server

• LLM‑driven agent discovery – let a language model dynamically find the best‑fit agent for a user request.
• Marketplace analytics dashboard – visualize traffic and popularity trends of AI agents.
• Automated agent publishing – CI pipelines can push new agents to the marketplace via the provided API.
• Cross‑platform tooling – integrate with browsers, IDE extensions, or custom assistants that need searchable agent data.

FAQ from the AI Agent Marketplace Index MCP Server

• Do I need a Bing Search API key? Yes, a Microsoft Bing Search API key is required to power the external web search feature.
• Can I run the server on Windows? Absolutely; just use the Windows‑specific activation command for the virtual environment.
• What Python version is supported? Python 3.10 or higher.
• How do I add my own tools? Implement a function following the search_ai_agent(q: str, limit: int = 100, timeout: int = 5) signature and register it in the MCP server’s tool list.
• Is the server open‑source? Yes, it is released under the MIT License.

AI Agent Marketplace Index Search MCP Server

MCP Server for AI Agent Marketplace Index from DeepNLP, , allowing AI assistants to searches available AI agents Navigation Page function, tools or use cases by "keywords" or "category". such as find all the "AI coding agents", "GUI AI Agents", "Mobile Use Agent", "Desktop Use Agent", etc.

Features

• Search AI Agents by query or category, find all available ai agents from the Agent Marketplace Index, such as "AI Coding", "HR AI Agents", "Finance AI Agent", "Healthcare AI Agent", "AI Agents Employees",etc.
• Monitor AI Agents Web Traffic Performance, such as Google/Bing ranking, Github Stars, Arxiv Reference.
• API to list your AI agents to the AI Agent Marketplace and Index
• Comprehensive error handling

Update

Add MCP Marketplace Plugin

Open Project https://github.com/AI-Agent-Hub/mcp-marketplace

Search Engine for AI Agents

Tool Listing

Tool Result

Requirements

• Python 3.10 or higher
• Microsoft Bing Search API key
• MCP-compatible client (e.g., Claude Desktop, Cursor)

Installation

1. Clone this repository
2. Install dependencies:

   uv venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate
   uv pip install -e .
   

Configuration

Usage

Running the server

uv run -m ai-agent-marketplace-index-mcp

development

cd ./ai-agent-marketplace-index-mcp/src/ai-agent-marketplace-index
mcp dev server.py

Configuring with Claude for Desktop

Add the following to your Claude Desktop configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
    "mcpServers": {
        "ai-agent-marketplace-index-mcp": {
            "command": "uv",
            "args": [
                "--directory",
                "/ABSOLUTE/PATH/TO/PARENT/FOLDER/ai-agent-marketplace-index-mcp/src/ai-agent-marketplace-index",
                "run",
                "server.py"
            ]
        }
    }
}

Available Tools

1. search_ai_agent

General search of AI Agents for information, websites, content and metric statistic of web traffic, etc.

search_ai_agent(q: str, limit: int = 100, timeout: int = 5)

Resources

MCP Marketplace API Support

• Allow any agent rag workflow to find this MCP Server via python/typescript API
• Search relevant servers by query/id/category
• Give LLM chances to choose this tools and enhance usage.

Example: Search Server and Tools

    import mcp_marketplace as mcpm
    mcpm.set_endpoint("deepnlp") # choose various open mcp marketplace endpoint

    result_q = mcpm.search(id="ai-agent-marketplace-index-mcp", mode="dict", page_id=0, count_per_page=100)
    result_id = mcpm.search(id="ai-agent-hub/ai-agent-marketplace-index-mcp", mode="dict", page_id=0, count_per_page=100)
    tools = mcpm.list_tools(id="ai-agent-hub/ai-agent-marketplace-index-mcp")

Example: Integrate with LLM e.g. Claude

    import anthropic
    client = anthropic.Anthropic()

    # Step 1. search mcp by query/id to find this mcp

    # Step 2. Calling LLM for Better Usage and MCP Selection
    response = client.messages.create(
        model="claude-3-7-sonnet-20250219", max_tokens=1024, tools=tools, messages=[]
    )
    print(response)
    ## install remote servers if tools from this mcp are chosen

License

MIT License