MCP Server

Chroma MCP

Vector search and document retrieval via the Chroma MCP server

Chroma is an open-source embedding database for building AI applications with vector search. The Chroma MCP server lets your agents query collections, add documents, and perform similarity search — enabling Retrieval-Augmented Generation (RAG) patterns in your workflows.

Official documentation

Setup

Set up Chroma

Run Chroma locally with Docker or deploy to Chroma Cloud. For local: docker run -p 8000:8000 chromadb/chroma. For Chroma Cloud, sign up at trychroma.com.

Chroma Docs

Add the integration in CipherSense Agents

Go to Project > Integrations > Add Integration > Chroma MCP. Enter your Chroma server URL and optional API key. CipherSense Agents auto-discovers collection tools via tools/list. Click Save & Test.

Connection Fields

Fields required when adding this integration in your Project › Integrations.

Field	Required	Description
SSE Endpoint URL	Required	SSE endpoint URL of your self-hosted Chroma MCP server.
Chroma API Key (Optional)	Optional	API key for your Chroma instance, if authentication is enabled.
Embedding Provider API Key (Optional)	Optional	API key for the embedding provider used by your Chroma instance (e.g. OpenAI).

Common Use Cases

RAG workflows with custom document collectionsSemantic similarity search for knowledge basesStore and query AI-generated embeddingsBuild long-term memory for agent workflows

Ready to connect Chroma MCP?

Add this integration from your project dashboard and wire it into a workflow.

Open Dashboard ← Back to Integrations