vespo92/chromadblocal-mcp-server
If you are the rightful owner of chromadblocal-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
ChromaDB MCP Server provides AI assistants with persistent memory using ChromaDB vector storage, enabling the creation of a growing knowledge base with each interaction.
ChromaDB MCP Server š§
A Model Context Protocol (MCP) server that gives AI assistants persistent memory through ChromaDB vector storage. Build your own knowledge base that grows with every interaction!
⨠Features
- Persistent AI Memory: Your AI assistant remembers past conversations and solutions
- Vector Search: Find similar code patterns, configurations, and documentation instantly
- Easy Integration: Works seamlessly with Claude Desktop and other MCP-compatible clients
- Home AI Ready: Pre-configured collections for personal projects and automation
- Local First: Run everything on your own hardware, no cloud dependencies
š Quick Start
Prerequisites
- Bun (JavaScript runtime)
- Docker (for ChromaDB)
- Claude Desktop (or any MCP client)
Installation
-
Clone the repository
git clone https://github.com//vespo92/chromadblocal-mcp-server.git cd chromadb-mcp-server
-
Install dependencies
bun install
-
Start ChromaDB
docker run -d \ --name chromadb-local \ -p 8001:8000 \ -v ~/chromadb-data:/chroma/chroma \ -e IS_PERSISTENT=TRUE \ chromadb/chroma:latest
-
Initialize collections
bun run setup
-
Configure Claude Desktop
Add to
~/Library/Application Support/Claude/claude_desktop_config.json
:{ "mcpServers": { "chromadb-context": { "command": "bun", "args": ["run", "/path/to/chromadb-mcp-server/index.js"], "env": { "CHROMADB_URL": "http://localhost:8001" } } } }
-
Restart Claude Desktop and start building your knowledge base!
š¬ Usage Examples
Once configured, interact naturally with your AI:
Store Knowledge
- "Store this Docker configuration in ChromaDB for future reference"
- "Save this React component pattern with tags: hooks, authentication"
- "Remember this solution for GPU passthrough issues"
Retrieve Information
- "Search ChromaDB for Python async examples"
- "Find similar component patterns to this one"
- "What solutions do we have for Docker networking issues?"
Build Context
- "Add this API documentation to the project_docs collection"
- "Store these test patterns for our testing suite"
š Available Collections
Collection | Description | Use Case |
---|---|---|
home_automation | Smart home configs & automations | Home Assistant, IoT scripts |
code_snippets | Reusable code patterns | Functions, hooks, utilities |
configurations | System & app configs | Docker, Kubernetes, services |
troubleshooting | Problem solutions | Fixes, workarounds, debugging |
project_docs | Project documentation | APIs, architecture, guides |
learning_notes | Learning insights | Tutorials, concepts, notes |
š ļø MCP Tools
search_context
Search for relevant information across collections
Parameters:
- query: Search query
- collection: (optional) Specific collection to search
- limit: (optional) Number of results
store_context
Store new information with metadata
Parameters:
- content: The content to store
- metadata: Tags, categories, descriptions
- collection: Target collection
list_collections
List all available collections and their metadata
find_similar_patterns
Find code patterns similar to provided example
š§ Configuration
Environment Variables
CHROMADB_URL=http://localhost:8001 # ChromaDB server URL
Custom Collections
Add new collections in setup-home-collections.js
:
await createCollection('ml_experiments', {
description: 'Machine learning experiments and results'
});
š¦ Project Structure
chromadb-mcp-server/
āāā index.js # MCP server implementation
āāā setup-home-collections.js # Collection initialization
āāā test-chromadb.js # Connection test script
āāā test-mcp.js # MCP functionality test
āāā HOME-AI-SETUP.md # Detailed setup guide
āāā package.json # Project dependencies
āāā README.md # This file
š¤ Contributing
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
See for more details.
š License
This project is licensed under the MIT License - see the file for details.
š Acknowledgments
- Anthropic for the MCP specification
- Chroma for the excellent vector database
- The open-source community for inspiration and support
š What's Next?
- Cloud sync capabilities
- Multi-user support
- Web UI for collection management
- Export/import collections
- Integration with more AI assistants
Built with ā¤ļø for the Home AI Community