by AI-Agent-Hub
ai-agent-marketplace-index-mcp is a Multi-Cloud Platform (MCP) server that functions as a search engine and monitoring tool for over 5000 AI agents and tools. It allows users to discover AI agents by keywords or categories and track their web traffic performance.
ai-agent-marketplace-index-mcp is an MCP (Multi-Cloud Platform) server developed by DeepNLP. It serves as a search engine and monitoring tool for the AI Agent Marketplace Index, which contains over 5000 AI agents and tools across various categories. It allows users to search for AI agents by keywords or categories and monitors their web traffic performance.
To use ai-agent-marketplace-index-mcp, you need Python 3.10 or higher, a Microsoft Bing Search API key, and an MCP-compatible client like Claude Desktop or Cursor.
Installation:
uv venv
, source .venv/bin/activate
, and uv pip install -e .
Running the server:
cd ./ai-agent-marketplace-index-mcp/src/ai-agent-marketplace-index
then mcp dev server.py
uv run -m ai-agent-marketplace-index-mcp
Configuring with Claude for Desktop: Add the provided JSON configuration to your Claude Desktop configuration file, adjusting the absolute path to the project.
Available Tool:
search_ai_agent(q: str, limit: int = 100, timeout: int = 5)
: General search of AI Agents for information, websites, content, and web traffic statistics.Integrating with LLMs (e.g., Claude):
Use the mcp_marketplace
library to search for the MCP server and list its tools, then integrate these tools into your LLM's message creation process.
search_ai_agent
tool to enhance their capabilities by finding and utilizing specific AI agents.Q: What are the system requirements? A: Python 3.10 or higher, a Microsoft Bing Search API key, and an MCP-compatible client (e.g., Claude Desktop, Cursor).
Q: How can I integrate this with my LLM?
A: You can use the mcp_marketplace
library to search for the server and list its tools, then pass these tools to your LLM for selection and usage.
Q: Can I list my own AI agent on the marketplace? A: Yes, the project provides an API for listing your AI agents to the AI Agent Marketplace and Index.
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.
Open Project https://github.com/AI-Agent-Hub/mcp-marketplace
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
uv pip install -e .
uv run -m ai-agent-marketplace-index-mcp
cd ./ai-agent-marketplace-index-mcp/src/ai-agent-marketplace-index
mcp dev server.py
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"
]
}
}
}
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)
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
Reviews feature coming soon
Stay tuned for community discussions and feedback