Is Chroma MCP free?
Yes, both Chroma and its MCP server are open-source and free under Apache 2.0 license.
DatabaseFreeactiveReviewed by MCPIndex
Chroma MCP
Connect Claude to Chroma vector database. Store, search, and retrieve embeddings using natural language for RAG and semantic memory workflows.
Looking for more MCP servers? Browse the full MCP tools directory or explore more tools in Database.
Quick overview
Chroma MCP bridges your AI assistant to Chroma, the open-source vector database. You can create collections, insert embeddings, run semantic searches, and retrieve documents directly from Claude Desktop. Ideal for building Retrieval-Augmented Generation (RAG) pipelines and persistent AI memory.
What this MCP server is best for
- Querying and inspecting data directly from your AI assistant with Chroma MCP.
- Debugging records, reviewing schemas, or validating application data quickly.
- Supporting developer workflows that need fast database access without context switching.
When to choose it
Choose Chroma MCP when your workflow depends on inspecting or querying structured data directly from an MCP-compatible AI assistant.
Good fit
vector-databaseembeddingsragsemantic-searchmemory
Chroma MCP Configuration
Use the following configuration as a starting point for Claude Desktop or any compatible MCP client, then replace placeholder credentials with your own values.
claude_desktop_config.json
{
"mcpServers": {
"chroma": {
"command": "npx",
"args": ["-y", "@chroma-core/mcp"],
"env": {
"CHROMA_URL": "http://localhost:8000"
}
}
}
}How to set up Chroma MCP
These setup steps cover the typical installation flow for this MCP server.
- 1
Install and run Chroma locally or use a cloud instance.
- 2
Add the config block to claude_desktop_config.json with your Chroma URL.
- 3
Restart Claude Desktop completely.
- 4
Ask Claude to list collections or search for similar documents.
Frequently asked questions
Common questions for Chroma MCP.
What can I use it for?
Mainly for RAG applications: store document embeddings, search for relevant context, and give Claude long-term memory via vector storage.
Do I need to run Chroma separately?
Yes, you need a running Chroma instance (local or cloud). The MCP server connects to it via the CHROMA_URL environment variable.
Chroma MCP vs Competitors
| Feature | Chroma MCP | Competitor |
|---|---|---|
| Vector Search | ✅ Yes | ❌ Limited |
| Open Source | ✅ Yes | ❌ Varies |
| RAG Support | ✅ Native | ❌ Manual |