# Chroma

> Embedded and hosted vector database for AI agents — open source, zero-ops.

[Canonical HTML page](https://top-mcps.com/mcp/chroma) · [server.json](https://top-mcps.com/mcp/chroma.json) · [methodology](https://top-mcps.com/about/methodology)

## Install

### Claude Desktop — `claude_desktop_config.json`

Paste under mcpServers. Fully quit and reopen Claude after editing.

```json
{
  "mcpServers": {
    "chroma": {
      "command": "uvx",
      "args": [
        "chroma-mcp"
      ],
      "env": {
        "CHROMA_PATH": "${CHROMA_PATH}",
        "CHROMA_HOST": "${CHROMA_HOST}",
        "CHROMA_API_KEY": "${CHROMA_API_KEY}"
      }
    }
  }
}
```

### Claude Code — `CLI or .mcp.json`

Run from your repo. Commit .mcp.json to share with your team.

```shell
# export CHROMA_PATH=./chroma_db
# export CHROMA_HOST=optional-for-server-mode
# export CHROMA_API_KEY=optional-for-cloud
claude mcp add chroma -- uvx chroma-mcp
```

### Cursor — `.cursor/mcp.json`

Global path: ~/.cursor/mcp.json. Reload window after editing.

```json
{
  "mcpServers": {
    "chroma": {
      "command": "uvx",
      "args": [
        "chroma-mcp"
      ],
      "env": {
        "CHROMA_PATH": "${CHROMA_PATH}",
        "CHROMA_HOST": "${CHROMA_HOST}",
        "CHROMA_API_KEY": "${CHROMA_API_KEY}"
      }
    }
  }
}
```

### VS Code — `.vscode/mcp.json`

VS Code uses the "servers" key (not "mcpServers").

```jsonc
{
  "servers": {
    "chroma": {
      "command": "uvx",
      "args": [
        "chroma-mcp"
      ],
      "env": {
        "CHROMA_PATH": "${CHROMA_PATH}",
        "CHROMA_HOST": "${CHROMA_HOST}",
        "CHROMA_API_KEY": "${CHROMA_API_KEY}"
      }
    }
  }
}
```

### Windsurf — `~/.codeium/windsurf/mcp_config.json`

Open via Cascade → hammer icon → Configure.

```json
{
  "mcpServers": {
    "chroma": {
      "command": "uvx",
      "args": [
        "chroma-mcp"
      ],
      "env": {
        "CHROMA_PATH": "${CHROMA_PATH}",
        "CHROMA_HOST": "${CHROMA_HOST}",
        "CHROMA_API_KEY": "${CHROMA_API_KEY}"
      }
    }
  }
}
```

### Cline — `cline_mcp_settings.json`

Open via the Cline sidebar → MCP Servers → Edit.

```json
{
  "mcpServers": {
    "chroma": {
      "command": "uvx",
      "args": [
        "chroma-mcp"
      ],
      "env": {
        "CHROMA_PATH": "${CHROMA_PATH}",
        "CHROMA_HOST": "${CHROMA_HOST}",
        "CHROMA_API_KEY": "${CHROMA_API_KEY}"
      }
    }
  }
}
```

### Continue — `~/.continue/config.json`

Continue uses modelContextProtocolServers with a transport block.

```json
{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "uvx",
          "args": [
            "chroma-mcp"
          ],
          "env": {
            "CHROMA_PATH": "${CHROMA_PATH}",
            "CHROMA_HOST": "${CHROMA_HOST}",
            "CHROMA_API_KEY": "${CHROMA_API_KEY}"
          }
        }
      }
    ]
  }
}
```

### Codex CLI — `~/.codex/config.toml`

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

```shell
# ~/.codex/config.toml
[mcp_servers.chroma]
command = "uvx"
args = [
  "chroma-mcp",
]
env = { CHROMA_PATH = "${CHROMA_PATH}", CHROMA_HOST = "${CHROMA_HOST}", CHROMA_API_KEY = "${CHROMA_API_KEY}" }
```

### Zed — `~/.config/zed/settings.json`

Zed calls them "context_servers". Settings live-reload on save.

```jsonc
{
  "context_servers": {
    "chroma": {
      "command": {
        "path": "uvx",
        "args": [
          "chroma-mcp"
        ]
      },
      "env": {
        "CHROMA_PATH": "${CHROMA_PATH}",
        "CHROMA_HOST": "${CHROMA_HOST}",
        "CHROMA_API_KEY": "${CHROMA_API_KEY}"
      }
    }
  }
}
```

### ChatGPT — `ChatGPT → Apps directory`

Chroma doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.

```none

```

## At a glance

- **Maintainer:** Chroma
- **Transport:** stdio
- **Auth model:** API key
- **Required secrets:** CHROMA_PATH, CHROMA_HOST, CHROMA_API_KEY
- **Supported clients:** Claude, Cursor, VS Code, Windsurf, Any MCP-compatible client, Chroma Cloud, Local Chroma
- **License:** Apache-2.0
- **Language:** Python
- **Latest version:** latest
- **Last verified:** 2026-06-02
- **GitHub stars:** 554 (fetched 2026-06-02T13:16:41.453Z)
- **Score:** 72/100 (rubric 2026-04 — see https://top-mcps.com/about/methodology)
- **Source:** https://github.com/chroma-core/chroma-mcp

## Tools & permissions

| Tool | Description | Args | Side effects |
|------|-------------|------|--------------|
| `list_collections` | List collections in the Chroma instance. | `—` | read |
| `create_collection` | Create a new collection. | `name: string` | write |
| `add_documents` | Add documents to a collection. | `collection: string, documents: array, metadatas?: array` | write |
| `query` | Run a semantic query with optional metadata filters. | `collection: string, query_text: string, n_results?: number` | read |

## Security & scope

- **Access scope:** read-write
- **Sandbox:** Local mode runs entirely in the MCP process — data lives at CHROMA_PATH. Cloud mode authenticates with an API key scoped to one tenant. No outbound network calls in local mode.
- **Gotchas:**
  - Local mode writes to disk on every add — back up the CHROMA_PATH directory if it matters.
  - Cloud API keys are full-tenant — scope by tenant rather than relying on collection-level isolation.
  - The default embedding function downloads model weights on first run — pre-warm in CI to avoid first-call latency.

## Quick answer

**What it does.** Connects to Chroma (in-process, persistent, or Cloud) and exposes collection management, document add/update, and semantic + metadata-filtered queries to AI models.

**Best for:**
- Persistent agent memory
- Personal knowledge base retrieval
- Document-grounded RAG
- Local prototyping of a vector pipeline
- Multi-collection scoping per project

**Not for:**
- Billion-scale workloads
- Production multi-tenant SaaS without operator attention
- Workloads that need built-in BM25 + vector hybrid

## Description

The official Chroma MCP connects an AI agent to a Chroma collection — the in-process vector database used as the default in LangChain, LlamaIndex, and many agent stacks. Add documents, run semantic queries, manage collections, and inspect embeddings. Works against an in-process Chroma, a persistent local path, or hosted Chroma Cloud.

## Why it matters

Most agents need persistent recall — and Chroma is the lowest-friction vector store for that. As an MCP it stops being a Python library buried in a backend and becomes a tool any MCP-capable agent can call.

## Key features

- In-process, persistent file, or Cloud modes
- Metadata filtering on queries
- Multiple-embedding-function support
- Per-collection isolation
- Apache-2.0 license

## FAQ

### Local or hosted?

Both. Set CHROMA_PATH for a local persistent file (the simplest mode), CHROMA_HOST for a self-hosted server, or pair CHROMA_API_KEY with a Cloud tenant URL for hosted Chroma.

### Which embedding function does it use?

Chroma's default embedding function for the collection — usually all-MiniLM-L6-v2 on local or a hosted model in Cloud. Switch per-collection if you need a specific dimensionality.

### Does it support metadata filters?

Yes. The query tool accepts a where filter (string equality, IN, NOT IN, comparison) and a where_document filter for inside-text search.

## Changelog

- **2026-06-02** — Refreshed install snippets and fact sheet; verified for 2026.
- **2025-02-08** — Initial directory listing.