Skip to main content

MCP server exposing the full SnapMind RAG backend capabilities as tools and resources

Project description

SnapMind MCP Server

smithery badge

The SnapMind Model Context Protocol (MCP) server exposes the powerful capabilities of the SnapMind RAG backend to any MCP-compatible client (like Cursor, Claude Desktop, or Antigravity).

Version 2.0 brings a massive expansion from 9 to 18 tools, deep reasoning agents, knowledge graph visualization, bookmarks, and site management.

Installation

Method 1: Using Smithery (Recommended)

To install SnapMind for Claude Desktop or other MCP clients via Smithery:

npx -y @smithery/cli install snapmind-mcp --client claude

Method 2: Manual Installation

  1. Clone the repository and navigate to the mcp-server directory:
git clone https://github.com/roshankumar0036singh/SnapMind.git
cd SnapMind/mcp-server
  1. Install dependencies:
pip install -e .
  1. Add to your MCP client configuration (e.g., claude_desktop_config.json or Cursor's MCP config):
{
  "mcpServers": {
    "snapmind": {
      "command": "snapmind-mcp",
      "env": {
        "SNAPMIND_BACKEND_URL": "https://snapmind-gateway.roshankumar30080.workers.dev",
        "GEMINI_API_KEY": "your-gemini-key",
        "MISTRAL_API_KEY": "your-mistral-key"
      }
    }
  }
}

Features

🛠️ 18 Available Tools

  • Search & Chat
    • snapmind_search - Semantic search across documents, bookmarks, and history.
    • snapmind_chat - Chat with your knowledge base using optional personas.
  • Knowledge Management
    • snapmind_create_bookmark / list_bookmarks / delete_bookmark - Manage saved snippets.
    • snapmind_knowledge_graph - Extract relations and nodes from your data.
    • snapmind_list_sites / delete_site - Manage indexed source websites.
    • snapmind_export_site - Export all data for a specific site.
  • Deep Research
    • snapmind_web_research - Multi-agent web research pipeline.
    • snapmind_deep_research - Multi-hop reasoning chain across web and local sources.
    • snapmind_generate_report - Synthesize sessions into a DOCX report.
  • Ingestion
    • snapmind_ingest_url - Index a website.
    • snapmind_ingest_file - Index local documents (PDF, DOCX, CSV).
    • snapmind_ingest_repo - Clone and index a GitHub repository.
  • Utilities
    • snapmind_translate - Translate text between languages.
    • snapmind_analyze_image - Vision AI (QA/OCR) on local images.
    • snapmind_list_personas / get_analytics / health_check

📚 7 Available Resources

  • snapmind://kb/stats - Live knowledge base statistics
  • snapmind://kb/tags - All semantic tags
  • snapmind://kb/sites - List of all indexed source URLs
  • snapmind://graph/full - The full knowledge graph data (JSON)
  • snapmind://graph/sessions - List of sessions containing graph data
  • snapmind://sessions/{id}/history - Chat history for a specific session

🗣️ 6 Prompt Templates

  • research_topic, code_review, summarize_notebook, deep_dive, compare_sources, export_knowledge

Development & Testing

# Run tests
pip install -e ".[dev]"
pytest tests/ -v

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

snapmind_mcp-2.0.0.tar.gz (13.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

snapmind_mcp-2.0.0-py3-none-any.whl (20.7 kB view details)

Uploaded Python 3

File details

Details for the file snapmind_mcp-2.0.0.tar.gz.

File metadata

  • Download URL: snapmind_mcp-2.0.0.tar.gz
  • Upload date:
  • Size: 13.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.13

File hashes

Hashes for snapmind_mcp-2.0.0.tar.gz
Algorithm Hash digest
SHA256 cb4da6518bdd213fb8c2a219f6ba10667d9d84e5cb79dd38703c45cfb4b648b9
MD5 287f3962450aa5413480305fbe2c26ae
BLAKE2b-256 c27f477f996a398093065164ba161ae63f3912ec1a537eafc42df7d89ab53491

See more details on using hashes here.

File details

Details for the file snapmind_mcp-2.0.0-py3-none-any.whl.

File metadata

  • Download URL: snapmind_mcp-2.0.0-py3-none-any.whl
  • Upload date:
  • Size: 20.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.13

File hashes

Hashes for snapmind_mcp-2.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5ceed35918c11e75004d5b54f4537515c136ac920c6f4e770df4dee55d0b25f9
MD5 1b72b3fab009fef0fc25674136040b59
BLAKE2b-256 a551e2994be5e9c9d6f7c2b7033dedcb3f5a6f434ee722584a15d3547309f788

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page