Chroma MCP Server

MCPOfficialOpen SourceApache-2.072.9

by chroma-core • Search & Retrieval

A self-hosted MCP server that exposes Chroma's vector database features (collections, semantic search, metadata filtering) to LLM agents and tools.

Example Use Cases

1
Persistent or ephemeral vector memory stores to save and retrieve conversational or application-specific context.
2
Perform semantic search, full-text search, and metadata-filtered retrieval across document collections.
3
A self-hosted or cloud-backed embedding database with configurable embedding functions and HNSW search tuning.

Description

This Model Context Protocol (MCP) server provides data retrieval backed by Chroma, enabling agents to create collections, add documents, and perform vector/semantic and full-text searches with advanced metadata filtering. It supports multiple client types (ephemeral, persistent/file-based, HTTP, and Chroma Cloud) and persists collection embedding configurations to simplify future queries and inserts. The server includes document management APIs (add, query, update, delete), HNSW tuning, and built-in embedding function integrations for several providers. It is intended for easy local self-hosting or connecting to Chroma Cloud for managed hosting.

Capabilities(13 total)

Tools (13)

chroma_list_collections

List all collection names in the Chroma database with pagination support. Args: limit: Optional maximum number of collections to return offset: Optional number of collections to skip before returning results Returns: List of collection names or ["__NO_COLLECTIONS_FOUND__"] if database is empty

limit:anyoffset:any

chroma_create_collection

Create a new Chroma collection with configurable HNSW parameters. Args: collection_name: Name of the collection to create embedding_function_name: Name of the embedding function to use. Options: 'default', 'cohere', 'openai', 'jina', 'voyageai', 'ollama', 'roboflow' metadata: Optional metadata dict to add to the collection

collection_name:string*embedding_function_name:stringmetadata:any

chroma_peek_collection

Peek at documents in a Chroma collection. Args: collection_name: Name of the collection to peek into limit: Number of documents to peek at

collection_name:string*limit:integer

chroma_get_collection_info

Get information about a Chroma collection. Args: collection_name: Name of the collection to get info about

collection_name:string*

chroma_get_collection_count

Get the number of documents in a Chroma collection. Args: collection_name: Name of the collection to count

collection_name:string*

Quick Actions

View on GitHub

Security

Scanned 3 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

B70/100

10/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFreemium

Capabilities13 Tools / 0 Prompts / 0 Resources

Ownerchroma-core

CategorySearch & Retrieval

DependenciesStandalone

Set Your Username