HyperStore MCP

<!-- mcp-name: io.github.deficlow/hyperstore-mcp -->

Plug 6,500+ AI apps into any LLM via the Model Context Protocol.

HyperStore is a curated directory of 6,500+ AI applications, developed by HyperGPT. This MCP server exposes the HyperStore catalog to any LLM client — Claude, ChatGPT, Cursor, Windsurf, Cline, Zed, Gemini, and anything else that speaks MCP.

Ask your LLM:

"Find me a free AI tool that summarises PDFs." "Compare ChatGPT, Claude, and Gemini side-by-side." "Show me the top 5 image-generation apps with an API."

The LLM calls HyperStore MCP behind the scenes and answers with up-to-date, curated results.

What you get

13 tools:

3 resources:

• hyperstore://app/{slug} — markdown rendering of any app
• hyperstore://category/{slug} — top apps in a category
• hyperstore://catalog — full category index

3 prompts:

• find_tool_for_task — guided discovery for a task
• compare_apps — side-by-side app comparison
• discover_category — explore a topic

Install

Option A — uvx (zero install, recommended)

Requires uv. One command and you're done:

uvx hyperstore-mcp

Option B — pipx

pipx install hyperstore-mcp
hyperstore-mcp

Option C — Docker (for remote hosting)

docker run --rm -p 8080:8080 ghcr.io/deficlow/hyperstore-mcp
# Now MCP Streamable HTTP at http://localhost:8080/mcp

Option D — Hosted endpoint (no install)

Use our managed Streamable HTTP server:

https://mcp.store.hypergpt.ai/mcp

Connect from your LLM client

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "hyperstore": {
      "command": "uvx",
      "args": ["hyperstore-mcp"]
    }
  }
}

Restart Claude → tools appear in the 🛠 menu.

Claude Code

claude mcp add hyperstore -- uvx hyperstore-mcp

Cursor

.cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "hyperstore": {
      "command": "uvx",
      "args": ["hyperstore-mcp"]
    }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "hyperstore": {
      "command": "uvx",
      "args": ["hyperstore-mcp"]
    }
  }
}

Cline (VS Code)

settings.json:

{
  "cline.mcpServers": {
    "hyperstore": {
      "command": "uvx",
      "args": ["hyperstore-mcp"]
    }
  }
}

Zed

~/.config/zed/settings.json:

{
  "context_servers": {
    "hyperstore": {
      "command": {
        "path": "uvx",
        "args": ["hyperstore-mcp"]
      }
    }
  }
}

Gemini CLI

~/.gemini/settings.json:

{
  "mcpServers": {
    "hyperstore": {
      "command": "uvx",
      "args": ["hyperstore-mcp"]
    }
  }
}

ChatGPT (Pro / Team / Enterprise)

Settings → Connectors → Add custom connector:

• Name: HyperStore
• MCP Server URL: https://mcp.store.hypergpt.ai/mcp
• Authentication: None

OpenAI Responses API

from openai import OpenAI

client = OpenAI()
response = client.responses.create(
    model="gpt-4.1",
    tools=[{
        "type": "mcp",
        "server_label": "hyperstore",
        "server_url": "https://mcp.store.hypergpt.ai/mcp",
        "require_approval": "never",
    }],
    input="Find me 3 free AI tools for writing unit tests.",
)
print(response.output_text)

Anthropic Messages API

from anthropic import Anthropic

client = Anthropic()
response = client.messages.create(
    model="claude-opus-4-7",
    max_tokens=1024,
    mcp_servers=[{
        "type": "url",
        "url": "https://mcp.store.hypergpt.ai/mcp",
        "name": "hyperstore",
    }],
    messages=[{"role": "user", "content": "Top 5 AI image generators?"}],
)

See examples/ for ready-to-paste configs for every supported client.

Self-hosting

For self-hosting, use the Docker image. For direct invocation without Docker, the CLI accepts --transport http|sse (see hyperstore-mcp --help).

Configuration

When self-hosting, these environment variables can be set (see .env.example for the full list):

Development

git clone https://github.com/deficlow/HyperStore-MCP
cd HyperStore-MCP
uv sync --all-extras
uv run pytest
uv run hyperstore-mcp        # stdio mode for local testing

Inspect the running server with the official MCP Inspector:

npx @modelcontextprotocol/inspector uvx hyperstore-mcp

How it works

HyperStore MCP is a thin async wrapper around the HyperStore public REST API. It is read-only — no credentials, no writes, no PII. The same data that powers the website powers the MCP server. Updates land in your LLM the moment they land on the site.

LLM client ──MCP──▶ hyperstore-mcp ──HTTPS──▶ store.hypergpt.ai/api

License

MIT © HyperGPT