HyperStore
About
Search and inspect 6,500+ curated AI apps from the HyperStore directory via 8 MCP tools, 3 resources, and 3 prompts. Read-only, no auth required. Works with Claude, ChatGPT, Cursor, Windsurf, Cline, Zed, Gemini.
Details
- Transport
- SSE
Explore
- Full-text keyword search (search_apps)
- Semantic/natural-language search (ai_search)
- Paginated app listings with filters (list_apps)
- Browse all 33 categories (list_categories)
- A‑Z directory browsing (browse_apps)
- Trending and featured apps from the homepage (get_homepage)
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
HyperStoreCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Requires](https://store.hypergpt.ai)uv. One command and you're done:
pipx install hyperstore-mcp hyperstore-mcp
docker run --rm -p 8080:8080 ghcr.io/deficlow/hyperstore-mcp # Now MCP Streamable HTTP at http://localhost:8080/mcp
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 mcp add hyperstore -- uvx hyperstore-mcp
.cursor/mcp.json(project) or~/.cursor/mcp.json(global):
{ "mcpServers": { "hyperstore": { "command": "uvx", "args": ["hyperstore-mcp"] } } }
{ "mcpServers": { "hyperstore": { "command": "uvx", "args": ["hyperstore-mcp"] } } }
{ "cline.mcpServers": { "hyperstore": { "command": "uvx", "args": ["hyperstore-mcp"] } } }
{ "context_servers": { "hyperstore": { "command": { "path": "uvx", "args": ["hyperstore-mcp"] } } } }
{ "mcpServers": { "hyperstore": { "command": "uvx", "args": ["hyperstore-mcp"] } } }
Settings → Connectors → Add custom connector:
- Name: HyperStore
- MCP Server URL:https://mcp.store.hypergpt.ai/mcp
- Authentication: None
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)
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?"}], )
Seeexamples/for ready-to-paste configs for every supported client.
For self-hosting, use theDocker image. For direct invocation without Docker, the CLI accepts--transport http|sse(seehyperstore-mcp --help).
When self-hosting, these environment variables can be set (see.env.examplefor the full list):
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 officialMCP Inspector:
npx @modelcontextprotocol/inspector uvx hyperstore-mcp
HyperStore MCP is a thin async wrapper around theHyperStorepublic REST API. It isread-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
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Living directory of x402 payment endpoints with curated recipes. Agents discover, evaluate, and execute paid workflows via MCP.
Search and discover 24,500+ MCP servers and AI agents. Semantic search, trust scores, vulnerability tracking.
Search 59,000+ MCP servers ranked by adoption and activity to find the right one for any task.
AI skills marketplace MCP server - search, discover, and install AI agent skills from SkillFlow.builders marketplace
A2A marketplace with 1800+ AI agents. Search, invoke, trade capabilities, datasets, prompts.
Search, discover, and install AI coding skills from SkillsMP marketplace with semantic search
RAG Search over your content powered by Inkeep
Production-ready RAG out of the box to search and retrieve data from your own documents.
An MCP server that connects to Perplexity's Sonar API, enabling real-time web-wide research in conversational AI.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"hyperstore": {
"server": {
"command": "uvx",
"args": [
"hyperstore-mcp"
]
}
}
}
}McpServers
{
"server": {
"command": "uvx",
"args": [
"hyperstore-mcp"
]
}
}Transport
"stdio"Package
"hyperstore-mcp"Registry
"pypi"Plug 6,500+ AI apps into any LLM via theModel Context Protocol.
HyperStoreis a curated directory of 6,500+ AI applications, developed byHyperGPT. This MCP server exposes theHyperStorecatalog to any LLM client — Claude, ChatGPT, Cursor, Windsurf, Cline, Zed, Gemini, and anything else that speaks MCP.
"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.
- hyperstore://app/{slug}— markdown rendering of any app
- hyperstore://category/{slug}— top apps in a category
- hyperstore://catalog— full category index
- find_tool_for_task— guided discovery for a task
- compare_apps— side-by-side app comparison
- discover_category— explore a topic
Option A —uvx(zero install, recommended)
Requiresuv. One command and you're done:
pipx install hyperstore-mcp hyperstore-mcp
docker run --rm -p 8080:8080 ghcr.io/deficlow/hyperstore-mcp # Now MCP Streamable HTTP at http://localhost:8080/mcp
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 mcp add hyperstore -- uvx hyperstore-mcp
.cursor/mcp.json(project) or~/.cursor/mcp.json(global):
{ "mcpServers": { "hyperstore": { "command": "uvx", "args": ["hyperstore-mcp"] } } }
{ "mcpServers": { "hyperstore": { "command": "uvx", "args": ["hyperstore-mcp"] } } }
{ "cline.mcpServers": { "hyperstore": { "command": "uvx", "args": ["hyperstore-mcp"] } } }
{ "context_servers": { "hyperstore": { "command": { "path": "uvx", "args": ["hyperstore-mcp"] } } } }
{ "mcpServers": { "hyperstore": { "command": "uvx", "args": ["hyperstore-mcp"] } } }
Settings → Connectors → Add custom connector:
- Name: HyperStore
- MCP Server URL:https://mcp.store.hypergpt.ai/mcp
- Authentication: None
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)
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?"}], )
Seeexamples/for ready-to-paste configs for every supported client.
For self-hosting, use theDocker image. For direct invocation without Docker, the CLI accepts--transport http|sse(seehyperstore-mcp --help).
When self-hosting, these environment variables can be set (see.env.examplefor the full list):
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 officialMCP Inspector:
npx @modelcontextprotocol/inspector uvx hyperstore-mcp
HyperStore MCP is a thin async wrapper around theHyperStorepublic REST API. It isread-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
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Living directory of x402 payment endpoints with curated recipes. Agents discover, evaluate, and execute paid workflows via MCP.
Search and discover 24,500+ MCP servers and AI agents. Semantic search, trust scores, vulnerability tracking.
Search 59,000+ MCP servers ranked by adoption and activity to find the right one for any task.
AI skills marketplace MCP server - search, discover, and install AI agent skills from SkillFlow.builders marketplace
A2A marketplace with 1800+ AI agents. Search, invoke, trade capabilities, datasets, prompts.
Search, discover, and install AI coding skills from SkillsMP marketplace with semantic search
RAG Search over your content powered by Inkeep
Production-ready RAG out of the box to search and retrieve data from your own documents.
An MCP server that connects to Perplexity's Sonar API, enabling real-time web-wide research in conversational AI.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
