Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@HokAI MCP Server What AI tools are available?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that exposes the HokAI catalogue of AI tools, agents, models, companies and infrastructure services to any MCP-compatible client.
Listed in the official MCP Registry as io.hokai/hokai.
The server is hosted, so you do not need to run anything locally:
https://hokai.io/mcpTransport: Streamable HTTP. No authentication required — the catalogue is public.
{
"mcpServers": {
"hokai": {
"type": "http",
"url": "https://hokai.io/mcp"
}
}
}Related MCP server: agentic-patterns
Tool | Description |
| Returns the full HokAI catalogue tree — AI tools, agents, models, companies and services, with categories. |
| Health check. Returns |
pip install "mcp[cli]" requests
python server.pyServes Streamable HTTP on 127.0.0.1:8000/mcp.
HokAI is an AI tool discovery platform. It catalogues AI tools, agents, models, companies and infrastructure providers with structured pricing, capability and comparison data — and Smart Match, which recommends tools from a plain-language description of what you are trying to do.
MIT
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Query the HokAI catalogue of AI tools, agents, models, companies and infrastructure services.
AgencyAI's public MCP for service discovery and AI-readiness assessment.
Read-only MCP server over the APIs.io catalog — discover APIs, providers, tags & artifacts.
AI agent registry — search, discover, register, and connect agents via MCP.
