{
  "markdown": "# HyperStore MCP\n\n<!-- mcp-name: io.github.deficlow/hyperstore-mcp -->\n\n> Plug 6,500+ AI apps into any LLM via the [Model Context Protocol](https://modelcontextprotocol.io).\n\n[![PyPI](https://img.shields.io/pypi/v/hyperstore-mcp.svg?label=pypi&color=3776AB)](https://pypi.org/project/hyperstore-mcp/)\n[![Glama](https://glama.ai/mcp/servers/deficlow/HyperStore-MCP/badges/score.svg)](https://glama.ai/mcp/servers/deficlow/HyperStore-MCP)\n[![Smithery](https://smithery.ai/badge/@deficlow/hyperstore)](https://smithery.ai/server/deficlow/hyperstore)\n[![MCP Registry](https://img.shields.io/badge/MCP%20Registry-listed-2D9CDB)](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.deficlow/hyperstore-mcp)\n[![CI](https://github.com/deficlow/HyperStore-MCP/actions/workflows/ci.yml/badge.svg)](https://github.com/deficlow/HyperStore-MCP/actions/workflows/ci.yml)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n\n**HyperStore** is a curated directory of 6,500+ AI applications, developed by [HyperGPT](https://hypergpt.ai).\nThis MCP server exposes the [HyperStore](https://store.hypergpt.ai) catalog to any LLM client — Claude, ChatGPT, Cursor,\nWindsurf, Cline, Zed, Gemini, and anything else that speaks MCP.\n\nAsk your LLM:\n\n> *\"Find me a free AI tool that summarises PDFs.\"*\n> *\"Compare ChatGPT, Claude, and Gemini side-by-side.\"*\n> *\"Show me the top 5 image-generation apps with an API.\"*\n\nThe LLM calls HyperStore MCP behind the scenes and answers with up-to-date, curated results.\n\n---\n\n## What you get\n\n**13 tools:**\n\n| Tool | Purpose |\n|---|---|\n| `search_apps` | Full-text keyword search |\n| `ai_search` | Embedding-based semantic search |\n| `get_app` | Full app detail (features, screenshots, pricing) |\n| `list_apps` | Paginated apps with filters (category, pricing) |\n| `list_categories` | Browse all 30+ categories |\n| `category_apps` | Apps within a category |\n| `browse_apps` | A-Z directory listing |\n| `get_homepage` | Trending + top categories overview |\n| `get_alternatives` | Curated alternatives to an app |\n| `list_audiences` | Audience segments (developers, lawyers, …) |\n| `apps_for_audience` | Best AI tools for an audience |\n| `list_use_cases` | Use-case taxonomies (legal-contracts, …) |\n| `apps_for_use_case` | AI tools for a use case |\n\n**3 resources:**\n\n- `hyperstore://app/{slug}` — markdown rendering of any app\n- `hyperstore://category/{slug}` — top apps in a category\n- `hyperstore://catalog` — full category index\n\n**3 prompts:**\n\n- `find_tool_for_task` — guided discovery for a task\n- `compare_apps` — side-by-side app comparison\n- `discover_category` — explore a topic\n\n---\n\n## Install\n\n### Option A — `uvx` (zero install, recommended)\n\nRequires [uv](https://docs.astral.sh/uv/). One command and you're done:\n\n```bash\nuvx hyperstore-mcp\n```\n\n### Option B — `pipx`\n\n```bash\npipx install hyperstore-mcp\nhyperstore-mcp\n```\n\n### Option C — Docker (for remote hosting)\n\n```bash\ndocker run --rm -p 8080:8080 ghcr.io/deficlow/hyperstore-mcp\n# Now MCP Streamable HTTP at http://localhost:8080/mcp\n```\n\n### Option D — Hosted endpoint (no install)\n\nUse our managed Streamable HTTP server:\n\n```\nhttps://mcp.store.hypergpt.ai/mcp\n```\n\n---\n\n## Connect from your LLM client\n\n### Claude Desktop\n\nEdit `~/Library/Application Support/Claude/claude_desktop_config.json`\n(macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n  \"mcpServers\": {\n    \"hyperstore\": {\n      \"command\": \"uvx\",\n      \"args\": [\"hyperstore-mcp\"]\n    }\n  }\n}\n```\n\nRestart Claude → tools appear in the 🛠 menu.\n\n### Claude Code\n\n```bash\nclaude mcp add hyperstore -- uvx hyperstore-mcp\n```\n\n### Cursor\n\n`.cursor/mcp.json` (project) or `~/.cursor/mcp.json` (global):\n\n```json\n{\n  \"mcpServers\": {\n    \"hyperstore\": {\n      \"command\": \"uvx\",\n      \"args\": [\"hyperstore-mcp\"]\n    }\n  }\n}\n```\n\n### Windsurf\n\n`~/.codeium/windsurf/mcp_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"hyperstore\": {\n      \"command\": \"uvx\",\n      \"args\": [\"hyperstore-mcp\"]\n    }\n  }\n}\n```\n\n### Cline (VS Code)\n\n`settings.json`:\n\n```json\n{\n  \"cline.mcpServers\": {\n    \"hyperstore\": {\n      \"command\": \"uvx\",\n      \"args\": [\"hyperstore-mcp\"]\n    }\n  }\n}\n```\n\n### Zed\n\n`~/.config/zed/settings.json`:\n\n```json\n{\n  \"context_servers\": {\n    \"hyperstore\": {\n      \"command\": {\n        \"path\": \"uvx\",\n        \"args\": [\"hyperstore-mcp\"]\n      }\n    }\n  }\n}\n```\n\n### Gemini CLI\n\n`~/.gemini/settings.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"hyperstore\": {\n      \"command\": \"uvx\",\n      \"args\": [\"hyperstore-mcp\"]\n    }\n  }\n}\n```\n\n### ChatGPT (Pro / Team / Enterprise)\n\n**Settings → Connectors → Add custom connector**:\n\n- **Name**: HyperStore\n- **MCP Server URL**: `https://mcp.store.hypergpt.ai/mcp`\n- **Authentication**: None\n\n### OpenAI Responses API\n\n```python\nfrom openai import OpenAI\n\nclient = OpenAI()\nresponse = client.responses.create(\n    model=\"gpt-4.1\",\n    tools=[{\n        \"type\": \"mcp\",\n        \"server_label\": \"hyperstore\",\n        \"server_url\": \"https://mcp.store.hypergpt.ai/mcp\",\n        \"require_approval\": \"never\",\n    }],\n    input=\"Find me 3 free AI tools for writing unit tests.\",\n)\nprint(response.output_text)\n```\n\n### Anthropic Messages API\n\n```python\nfrom anthropic import Anthropic\n\nclient = Anthropic()\nresponse = client.messages.create(\n    model=\"claude-opus-4-7\",\n    max_tokens=1024,\n    mcp_servers=[{\n        \"type\": \"url\",\n        \"url\": \"https://mcp.store.hypergpt.ai/mcp\",\n        \"name\": \"hyperstore\",\n    }],\n    messages=[{\"role\": \"user\", \"content\": \"Top 5 AI image generators?\"}],\n)\n```\n\nSee [`examples/`](examples/) for ready-to-paste configs for every supported client.\n\n---\n\n## Self-hosting\n\nFor self-hosting, use the [Docker image](#option-c--docker-for-remote-hosting).\nFor direct invocation without Docker, the CLI accepts `--transport http|sse`\n(see `hyperstore-mcp --help`).\n\n---\n\n## Configuration\n\nWhen self-hosting, these environment variables can be set\n(see [`.env.example`](.env.example) for the full list):\n\n| Variable | Default | Purpose |\n|---|---|---|\n| `MCP_HOST` | `0.0.0.0` | Bind host (http/sse transports) |\n| `MCP_PORT` | `8080` | Bind port (http/sse transports) |\n| `LOG_LEVEL` | `INFO` | Logging level (`DEBUG`, `INFO`, `WARNING`, `ERROR`) |\n\n---\n\n## Development\n\n```bash\ngit clone https://github.com/deficlow/HyperStore-MCP\ncd HyperStore-MCP\nuv sync --all-extras\nuv run pytest\nuv run hyperstore-mcp        # stdio mode for local testing\n```\n\nInspect the running server with the official **MCP Inspector**:\n\n```bash\nnpx @modelcontextprotocol/inspector uvx hyperstore-mcp\n```\n\n---\n\n## How it works\n\nHyperStore MCP is a thin async wrapper around the [HyperStore](https://store.hypergpt.ai) public\nREST API. It is **read-only** — no credentials, no writes, no PII. The same data that\npowers the website powers the MCP server. Updates land in your LLM the moment they\nland on the site.\n\n```\nLLM client ──MCP──▶ hyperstore-mcp ──HTTPS──▶ store.hypergpt.ai/api\n```\n\n---\n\n## License\n\nMIT © [HyperGPT](https://hypergpt.ai)\n",
  "bytes": 7002,
  "sha": "7856be0fd934f2543537d9ab9fb9afc60b958c6a8b2470762b2000c1474f0848",
  "repo_slug": "deficlow/hyperstore-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_deficlow_hyperstore_mcp_ac69270c/readme"
}