Vedic AI MCP Server
Model Context Protocol server for accessing Vedic scriptures and AI-powered philosophical Q&A
Overview
The Vedic AI MCP Server enables Large Language Models (Claude, GPT-4, etc.) to directly access Vedic scriptures and get AI-powered answers to philosophical questions through standardized tools defined by the Model Context Protocol.
Features
🛠️ Tools (Functions LLMs can call)
- search_vedic_scriptures - Search across all Vedic texts for relevant verses
- get_scripture_verse - Retrieve a specific verse with Sanskrit, transliteration, and translation
- list_scriptures - Get all available scriptures (Bhagavad Gita, 4 Vedas)
- get_scripture_chapters - List all chapters in a scripture
- ask_vedic_question - Ask philosophical questions with AI-powered answers grounded in scriptures
Installation
Prerequisites
- Python 3.11 or higher
- Access to Vedic AI Platform API (get your API key at https://mysticvedic.com)
Setup
-
Clone the repository (if not already done):
cd vedic-ai-platform/mcp-server
-
Install dependencies:
pip install -r requirements.txt
-
Configure environment:
cp .env.example .env # Edit .env to add your API credentials
-
Configure in Claude Desktop (or other MCP client):
Edit your
claude_desktop_config.json:macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:%APPDATA%\Claude\claude_desktop_config.json{ "mcpServers": { "vedic-ai": { "command": "python", "args": [ "/absolute/path/to/vedic-ai-platform/mcp-server/src/server.py" ], "env": { "VEDIC_AI_API_URL": "https://api.mysticvedic.com/api/v1", "VEDIC_AI_API_KEY": "your_api_key_here" } } } }
-
Restart Claude Desktop to load the MCP server
Usage
Once configured, you can ask Claude questions like:
- "Search for verses about karma in Bhagavad Gita"
- "Get me verse 2:47 from Bhagavad Gita"
- "What scriptures are available?"
- "Ask a Vedic question: What is the nature of the self?"
Claude will automatically use the appropriate tools to access the Vedic knowledge base.
Configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
VEDIC_AI_API_URL |
Base URL of Vedic AI API | http://localhost:8000/api/v1 |
VEDIC_AI_API_KEY |
Your API key for authentication | (required) |
MCP_SERVER_NAME |
Server identifier | vedic-ai |
MCP_SERVER_VERSION |
Server version | 1.0.0 |
Development
Project Structure
mcp-server/
├── src/
│ ├── __init__.py
│ ├── server.py # Main MCP server
│ ├── api_client.py # API client for backend
│ └── tools/
│ ├── __init__.py
│ ├── search.py # Search tools
│ ├── scriptures.py # Scripture tools
│ └── query.py # Query tools
├── tests/
├── requirements.txt
├── .env.example
└── README.md
Running Tests
pytest tests/
Code Formatting
black src/
ruff check src/
Available Tools Reference
search_vedic_scriptures
Search for verses across all scriptures.
Parameters:
query(string, required): Search queryscriptures(array, optional): Filter by specific scriptureslimit(number, optional): Max results (default: 5, max: 20)
Example:
{
"query": "What is dharma?",
"scriptures": ["bhagavad_gita"],
"limit": 3
}
get_scripture_verse
Get a specific verse.
Parameters:
scripture_id(string, required):bhagavad_gita,rig_veda, etc.chapter(number, required): Chapter numberverse(number, required): Verse number
Example:
{
"scripture_id": "bhagavad_gita",
"chapter": 2,
"verse": 47
}
list_scriptures
Get all available scriptures. No parameters required.
get_scripture_chapters
Get chapters from a scripture.
Parameters:
scripture_id(string, required): Scripture identifier
Example:
{
"scripture_id": "bhagavad_gita"
}
ask_vedic_question
Ask a philosophical question.
Parameters:
question(string, required): Your questioncontext(string, optional): Additional context
Example:
{
"question": "What is the nature of consciousness according to Vedic philosophy?",
"context": "I'm interested in understanding the relationship between Atman and Brahman"
}
Troubleshooting
Server not appearing in Claude
- Check that
claude_desktop_config.jsonis in the correct location - Verify the absolute path to
server.pyis correct - Ensure Python is in your PATH
- Check Claude Desktop logs:
~/Library/Logs/Claude/(macOS)
API Connection Errors
- Verify
VEDIC_AI_API_URLis correct - Check your API key is valid
- Ensure you have internet connectivity
- Test the API directly:
curl https://api.mysticvedic.com/api/v1/health
Import Errors
# Reinstall dependencies
pip install -r requirements.txt --upgrade
Contributing
See the main project CONTRIBUTING.md for guidelines.
License
See LICENSE
Support
- Documentation: https://docs.mysticvedic.com
- API Issues: https://github.com/vedic-ai/platform/issues
- Email: support@mysticvedic.com
Related Links
Metadata
Release files for vedic-ai-mcp-server 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| vedic_ai_mcp_server-1.0.0.tar.gz | 12.1 kB | Without provenance | Details for vedic_ai_mcp_server-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| vedic_ai_mcp_server-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for vedic_ai_mcp_server-1.0.0-py3-none-any.whl |
Total release size: 23.5 kB
Release files / vedic_ai_mcp_server-1.0.0.tar.gz
| Download URL | vedic_ai_mcp_server-1.0.0.tar.gz |
|---|---|
| Size | 12.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
22853e03c6f13a5895f41cf01102ef4095b3f1fa424c8b96ec34253cc59388d5
|
|
BLAKE2b-256 checksum How to use checksums |
272fc723525add30ceb99b04ee90c4e24e4c3b062bf8c5c8e67374b0a424c612
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.3
|
Release files / vedic_ai_mcp_server-1.0.0-py3-none-any.whl
| Download URL | vedic_ai_mcp_server-1.0.0-py3-none-any.whl |
|---|---|
| Size | 11.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c17a31472bde7c777fb0274c2cd5513186b15071327500df05eca75d3c84a140
|
|
BLAKE2b-256 checksum How to use checksums |
80c9d095d2b6d21b2e6442a1c500949306a0ab6c81dc0449cb4469a67baf1b37
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.3
|
Security for vedic-ai-mcp-server 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.