MCP For Claude Marketplace
Chroma (Vector DB)

Chroma (Vector DB) MCP Connector for Claude

A+

Manage vector embeddings via Chroma — list collections, query embeddings, and audit document counts directly from any AI agent.

7 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Chroma vector database to any AI agent and take full control of your semantic data through natural conversation.

What you can do

  • Vector Collections — List all available collections and inspect their deep configuration and metadata
  • Semantic Search — Perform high-dimensional vector similarity searches to find relevant context for your LLM applications
  • Document Auditing — Count documents, peek at unstructured data segments, and retrieve specific records by ID
  • Instance Health — Monitor heartbeats and connectivity across Chroma Cloud or self-hosted instances
  • Tenant & Database Management — Switch between different tenants and databases to isolate your production and staging environments

How it works

  1. Subscribe to this server
  2. Enter your Chroma URL (Cloud or self-hosted) and your API Key
  3. Start querying your embeddings from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Developers — test and debug vector search logic using natural language without writing Python scripts
  • Data Engineers — audit collection volumes and metadata consistency across different environments
  • Product Managers — inspect what context is being fed to AI agents by peeking at stored embeddings
  • DevOps Teams — monitor instance connectivity and health through automated heartbeats
embeddingssemantic-searchllm-infrastructurevector-searchdata-retrievalmachine-learning

7 tools expose this connector's capabilities to your AI agent.

list_collections

List all explicitly defined Vector Collections within a given tenant database

check_heartbeat

Validate fundamental network availability against explicit Chroma API nodes

get_collection

Identify bounded logical settings configuring a specific Vector Collection block

peek_documents

Extracts explicitly attached bounded preview of the Database limits

count_documents

Execute explicit structural tracking enumerating total document volumes

get_documents

Retrieve exact physical documents and semantic context inside known arrays

query_embeddings

Identify precise logical bounds matching high-dimensional semantic clustering

See how to talk to your AI agent using Chroma (Vector DB).

List all vector collections

I found 3 collections: 'knowledge-base', 'user-embeddings', and 'staging-docs'. Would you like to check the document count for any of them?

Peek at the first 5 documents in 'knowledge-base'

Peeking into 'knowledge-base'... Here are the first 5 documents. They contain technical documentation about our API endpoints and authentication flows. Each has metadata like 'source' and 'last_updated'.

Is the Chroma server alive?

Checking heartbeat... Connection successful! The Chroma instance responded in 12ms and is fully operational.

Yes. Provide the vector embedding array in JSON format, and your agent will return the closest document matches along with their distance metrics. It is the perfect way to test your RAG (Retrieval-Augmented Generation) logic without complex scripts.

Related Connectors

Vertex AI Vector Search

Vertex AI Vector Search MCP

6 tools Official

Bring Google's massive vector matching power to your AI agent. Search billions of semantic embeddings and administer Vertex Index endpoints directly in chat.

A+ View details →
Milvus (Open-Source Vector Database)

Milvus (Open-Source Vector Database) MCP

7 tools Official

Manage vector storage via Milvus — perform ANN searches, query scalar entities, and audit collections.

A+ View details →
Vald

Vald MCP

6 tools Official

Power your agent with Vald — query, insert, and manage dense vectors on a highly scalable, distributed nearest-neighbor engine.

A+ View details →
Gumlet

Gumlet MCP

12 tools Official

Optimize images and stream video with automatic format conversion, lazy loading, and CDN delivery that loads pages faster.

A+ View details →