An official MCP server for the Chroma open-source embedding database. Enables AI agents to create collections, add documents, perform vector search, full-text search, and metadata filtering through the Model Context Protocol.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Chroma MCP Server for Embedding Database Operations"
slug: "chroma-mcp-server-embedding-database-operations"
description: "An official MCP server for the Chroma open-source embedding database. Enables AI agents to create collections, add documents, perform vector search, full-text search, and metadata filtering through the Model Context Protocol."
github_stars: 527
verification: "security_reviewed"
source: "https://github.com/chroma-core/chroma-mcp"
category: "Integrations & Connectors"
framework: "MCP"
tool_ecosystem:
github_repo: "chroma-core/chroma-mcp"
github_stars: 527
---
# Chroma MCP Server for Embedding Database Operations
An official MCP server for the Chroma open-source embedding database. Enables AI agents to create collections, add documents, perform vector search, full-text search, and metadata filtering through the Model Context Protocol.
## Installation
Requirements and caveats from upstream:
- The fastest way to build Python or JavaScript LLM apps with memory!
Basic usage or getting-started notes:
- [The Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is an open protocol designed for effortless integration between LLM applications and external data sources or tools, offering a standard...
- To add an ephemeral client, add the following to your claude_desktop_config.json file:
- json
- Source: https://github.com/chroma-core/chroma-mcp
- Extracted from upstream docs: https://raw.githubusercontent.com/chroma-core/chroma-mcp/HEAD/README.md
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/chroma-mcp-server-embedding-database-operations/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.