MoreAI.tools
C
ChromaDB MCP
38
Stack Score
Editorial pick✓ Verified workingMCP server
ChromaDB MCP logo

ChromaDB MCP

Query and write to ChromaDB vector collections.

Try ChromaDB MCP

Best for

Best for prototypes and small RAG systems that want a fast local vector store.

At a glance

Pricing
open-source
Setup time
20 minutes
Learning curve
easy
Last verified
5/27/2026

What we love

  • ✓Open-source
  • ✓Easy local-first setup
  • ✓Lightweight RAG store

Where it falls short

  • −Less performant than Pinecone at scale
  • −Cloud option still maturing
  • −Backups manual on self-host

Install & connect

Copy-paste ready

Install
shell
uvx chroma-mcp
Config — Claude Desktop
json
{
  "mcpServers": {
    "chroma": {
      "command": "uvx",
      "args": ["chroma-mcp"]
    }
  }
}

Pricing

✓ Pricing verified Jun 21, 2026

1 tier

Open-source

$0

perpetual

  • ✓Apache 2.0

Overview

MCP server for ChromaDB — collection management, embedding upsert, nearest-neighbor search. Ideal local-first RAG vector store for Claude.

Key features

  • ●Collection CRUD
  • ●Embedding upsert
  • ●k-NN search
  • ●Metadata filters
  • ●Local + cloud

Exposed tools

The MCP-tool names this server exposes. Your agent can invoke any of these when this server is connected.

  • chroma_list_collections
    List all collections with pagination support.
  • chroma_create_collection
    Create a new collection with optional HNSW configuration.
  • chroma_peek_collection
    View a sample of documents in a collection.
  • chroma_get_collection_info
    Get detailed information about a collection.
  • chroma_get_collection_count
    Get the number of documents in a collection.
  • chroma_modify_collection
    Update a collection's name or metadata.
  • chroma_delete_collection
    Delete a collection.
  • chroma_add_documents
    Add documents with optional metadata and custom IDs.
  • chroma_query_documents
    Query documents using semantic search with advanced filtering.
  • chroma_get_documents
    Retrieve documents by IDs or filters with pagination.
  • chroma_update_documents
    Update existing documents' content, metadata, or embeddings.
  • chroma_delete_documents
    Delete specific documents from a collection.

Best use cases

Local RAG store

Run a fast local vector store for desktop AI agents.

Document indexing

Index company documents into Chroma for Claude RAG.

Integrations

ChromaDB
LangChain
LlamaIndex
OpenAI embeddings

Similar tools

See all analytics →
Hotjar
58
Heatmaps, session recordings, and surveys.
Mixpanel
55
Event analytics for product teams.
Amplitude
52
Product analytics and experimentation platform.
Compare side-by-side
ChromaDB MCP vs Hotjar vs Mixpanel
Pros, cons, pricing, role-fit — all on one page.
Open comparison

One AI Stack pick every week.

The tool we’d pay for this week, why we’d pay for it, and what we’d skip. No promo spam.