# Chroma (MCP Server)

> Create collections and add, query and manage documents in Chroma

- Type: MCP server
- Publisher: Chroma (official)
- Categories: AI & ML, Development, Data & Analytics
- Website: https://github.com/chroma-core/chroma-mcp
- Source: https://github.com/chroma-core/chroma-mcp
- Transport: stdio
- Launch command: uvx chroma-mcp
- Sign-in: api-key
- Environment variables: CHROMA_CLIENT_TYPE, CHROMA_API_KEY, CHROMA_TENANT, CHROMA_DATABASE
- GitHub stars: 598
- Listed: 2025-02-11

## About

Chroma's official MCP server gives agents collection management and document operations on Chroma, including full-text, metadata and vector search. It supports ephemeral, persistent, self-hosted HTTP and Chroma Cloud clients via uvx.

## Install

1. **Add the server to Codex**

   Codex CLI:

   ```bash
   codex mcp add chroma --env CHROMA_CLIENT_TYPE=YOUR_CHROMA_CLIENT_TYPE --env CHROMA_API_KEY=YOUR_CHROMA_API_KEY --env CHROMA_TENANT=YOUR_CHROMA_TENANT --env CHROMA_DATABASE=YOUR_CHROMA_DATABASE -- uvx chroma-mcp
   ```

   config.toml:

   ```toml
   [mcp_servers.chroma]
   command = "uvx"
   args = ["chroma-mcp"]
   
   [mcp_servers.chroma.env]
   CHROMA_CLIENT_TYPE = "YOUR_CHROMA_CLIENT_TYPE"
   CHROMA_API_KEY = "YOUR_CHROMA_API_KEY"
   CHROMA_TENANT = "YOUR_CHROMA_TENANT"
   CHROMA_DATABASE = "YOUR_CHROMA_DATABASE"
   ```

   Agents SDK:

   ```python
   from agents import Agent, Runner
   from agents.mcp import MCPServerStdio
   
   async with MCPServerStdio(
       name="Chroma",
       params={"command": "uvx", "args": ["chroma-mcp"]},
   ) as server:
       agent = Agent(name="Assistant", mcp_servers=[server])
       result = await Runner.run(agent, "Create a collection called meeting-notes")
       print(result.final_output)
   ```

## Tools

- `chroma_list_collections`
- `chroma_create_collection`
- `chroma_peek_collection`
- `chroma_get_collection_info`
- `chroma_get_collection_count`
- `chroma_modify_collection`
- `chroma_delete_collection`
- `chroma_add_documents`
- `chroma_query_documents`
- `chroma_get_documents`
- `chroma_update_documents`
- `chroma_delete_documents`

## Example prompts

- "Create a collection called meeting-notes"
- "Add these three documents to my notes collection"
- "Query my collection for anything about Q3 budget"
- "Peek at the first 5 documents in my collection"

## Related

- [Chrome DevTools MCP](https://chatgptplugins.directory/mcp/chrome-devtools.md): Let coding agents control and debug a live Chrome browser
- [Playwright MCP](https://chatgptplugins.directory/mcp/playwright.md): Browser automation for agents via Playwright accessibility snapshots
- [GitHub](https://chatgptplugins.directory/mcp/github.md): Manage repos, issues, pull requests and Actions from your AI agent
- [Context7](https://chatgptplugins.directory/mcp/context7.md): Pull up-to-date, version-specific library docs into your coding agent
- [Supabase](https://chatgptplugins.directory/mcp/supabase.md): Manage Supabase databases, migrations, edge functions and logs
- [Stripe](https://chatgptplugins.directory/mcp/stripe.md): Query and act on your Stripe account and search Stripe docs from any agent

---
Source: https://chatgptplugins.directory/mcp/chroma · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.