AI Skill Hub 推荐使用:Chroma 向量存储 是一款优质的MCP工具。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
提供远程MCP服务,支持ChromaDB。
Chroma 向量存储 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
提供远程MCP服务,支持ChromaDB。
Chroma 向量存储 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/meloncafe/chromadb-remote-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"chroma-----": {
"command": "npx",
"args": ["-y", "chromadb-remote-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Chroma 向量存储 执行以下任务... Claude: [自动调用 Chroma 向量存储 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"chroma_____": {
"command": "npx",
"args": ["-y", "chromadb-remote-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
A Streamable HTTP MCP (Model Context Protocol) server that provides remote access to ChromaDB for AI assistants like Claude. Enables semantic search and vector database operations from mobile devices and remote locations.
Note: This project uses MCP Streamable HTTP (2025-03-26 spec). SSE transport is deprecated.
---
┌──────────────────────────────┐ ┌──────────────┐
│ Claude Desktop + Mobile │ │ Claude Code │
│ (Custom Connector - synced) │ │ (CLI setup) │
└──────────────┬───────────────┘ └──────┬───────┘
│ │
│ MCP Remote Connector │
└─────────────┬───────────────┘
│ HTTPS
┌─────────▼──────────┐
│ Remote MCP │
│ Server (Node.js) │
│ │
│ • Auth Gateway │
│ • MCP Protocol │
│ • REST API Proxy │
└─────────┬──────────┘
│
┌─────────▼──────────┐
│ ChromaDB │
│ (Vector Database) │
│ │
│ • Embeddings │
│ • Collections │
│ • Semantic Search │
└────────────────────┘
How Clients Connect:
claude mcp add CLI command.All clients access the same self-hosted ChromaDB through this remote MCP server. Vector embeddings and semantic search results persist across all platforms.
Remote MCP server that enables all Claude clients (Desktop, Code, Mobile) to access the same self-hosted ChromaDB instance.
---
yarn install
curl -fsSL https://raw.githubusercontent.com/meloncafe/chromadb-remote-mcp/release/scripts/install.sh | bash
This will:
docker-compose.yml and .env.exampledocker-compose or docker compose)```bash
docker compose -f docker-compose.dev.yml up -d
#### Option 3: Local Development
bash
git clone https://github.com/meloncafe/chromadb-remote-mcp.git cd chromadb-remote-mcp yarn install
yarn build yarn start ```
```
Supported authentication methods (v2.0.0):
Authorization: Bearer TOKEN — only supported way to send MCP_AUTH_TOKEN.curl -H "Authorization: Bearer YOUR_TOKEN" https://your-server.com/mcpOIDC_ISSUERS (comma-separated issuer URLs) or OIDC_PRESET=google,github,microsoft.OIDC_AUDIENCE to the resource identifier (typically your MCP server's public URL)./.well-known/oauth-protected-resource.WWW-Authenticate: Bearer error="...", resource_metadata="..." per RFC 6750.Removed in v2.0.0:X-Chroma-Tokenheader and?apiKey=/?token=/?api_key=query-parameter auth are no longer accepted. Clients that previously used those paths must migrate toAuthorization: Bearer. TheALLOW_QUERY_AUTHenv var is ignored.
client = chromadb.HttpClient( host="your-server.com", port=443, ssl=True, headers={ "Authorization": "Bearer YOUR_TOKEN" } )
curl -L https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64 -o cloudflared chmod +x cloudflared
docker run -d -p 8000:8000 chromadb/chroma:latest
```bash
yarn build
```bash
yarn docker:build:local
yarn docker:build
./scripts/build.sh --version 1.2.3
./scripts/build.sh --repo myuser/my-mcp --version dev
#### Push to Docker Hub
bash
yarn docker:build:local
docker-compose up
./scripts/build.sh --version 1.2.3 --push ```
services:
mcp-server:
image: devsaurus/chromadb-remote-mcp:2.0.0
environment:
EMBEDDING_PROVIDER: gemini
EMBEDDING_MODEL: gemini-embedding-001
EMBEDDING_DIMENSIONS: "1536"
GEMINI_API_KEY: ${GEMINI_API_KEY}
OIDC_PRESET: google
OIDC_AUDIENCE: ${OIDC_AUDIENCE} # e.g. your client_id
CONFIDENCE_THRESHOLD: "0.55"
RERANKER_API_BASE: "http://desktop-gpu.tail-xxxx.ts.net:8001"
RERANKER_MODEL: bge-reranker-v2-m3
node -e "console.log(require('crypto').randomBytes(32).toString('base64url'))"
```python import chromadb
collection = client.create_collection("my_collection") collection.add( documents=["Document 1", "Document 2"], ids=["id1", "id2"] ) results = collection.query(query_texts=["query"], n_results=2)
Alternative authentication:
python from chromadb.config import Settings
client = chromadb.HttpClient( host="your-server.com", port=443, ssl=True, settings=Settings( chroma_client_auth_provider="chromadb.auth.token_authn.TokenAuthClientProvider", chroma_client_auth_credentials="YOUR_TOKEN" ) ) ```
mkdir chromadb-remote-mcp && cd chromadb-remote-mcp curl -O https://raw.githubusercontent.com/meloncafe/chromadb-remote-mcp/release/docker-compose.yml curl -O https://raw.githubusercontent.com/meloncafe/chromadb-remote-mcp/release/.env.example
cp .env.example .env
cp .env.example .env
cp .env.example .env
All configuration is done through the .env file. Copy .env.example to .env and customize:
cp .env.example .env
| Variable | Description | Default | Required |
|---|---|---|---|
PORT | External port (Caddy reverse proxy) | 8080 | No |
CHROMA_DATA_PATH | ChromaDB data storage path (volume name, ./data, or absolute path) | chroma-data | No |
CHROMA_HOST | ChromaDB host (internal) | chromadb | No |
CHROMA_PORT | ChromaDB port (internal) | 8000 | No |
CHROMA_TENANT | ChromaDB tenant | default_tenant | No |
CHROMA_DATABASE | ChromaDB database | default_database | No |
MCP_AUTH_TOKEN | Authentication token for MCP and REST API | - | **Yes** (for public access) |
CHROMA_AUTH_TOKEN | ChromaDB auth token (if ChromaDB requires auth) | - | No |
RATE_LIMIT_MAX | Max requests per IP per 15 minutes | 100 | No |
ALLOWED_ORIGINS | Comma-separated list of allowed origins (DNS rebinding protection) | - | No |
ChromaDB data can be stored in three ways:
CHROMA_DATA_PATH=chroma-datadocker volume ls and docker volume inspect chroma-data to locateCHROMA_DATA_PATH=./data3. Custom path: CHROMA_DATA_PATH=/path/to/data - Must be an absolute path - Useful for mounting external storage
After changing CHROMA_DATA_PATH, restart the services:
docker compose restart
---
Secure access within your Tailscale network:
```bash
To use Claude Desktop UI Custom Connector or share publicly:
```bash
```bash
server {
listen 80;
server_name your-domain.com;
location / {
proxy_pass http://localhost:3000;
proxy_http_version 1.1;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
}
}
---
claude mcp remove chromadb
./scripts/test.sh --help
**Integration Test Coverage:**
- ✅ Health check endpoint
- ✅ Authentication (`Authorization: Bearer` MCP_AUTH_TOKEN; OAuth 2.1 / OIDC multi-provider)
- ✅ MCP protocol (tools/list, tools/call)
- ✅ ChromaDB REST API proxy
- ✅ Collection CRUD operations
- ✅ Rate limiting
- ✅ Unauthorized access handling
**Unit Tests:**
bash
v2.0 introduces collection metadata schema v2, OAuth 2.1 OIDC, configurable embedding providers, and an optional reranker. See MIGRATION.md for the upgrade guide.
| Variable | Purpose |
|---|---|
EMBEDDING_PROVIDER | chromadb-default (English-only, default) / external / openai_compatible / gemini / voyage |
EMBEDDING_MODEL | Provider-specific model id. Stored in collection metadata. |
EMBEDDING_DIMENSIONS | Vector dimensions. Required for external mode; Gemini accepts 768/1536/3072. |
EMBEDDING_API_BASE | OpenAI-compatible endpoint base URL (Ollama / TEI / Voyage / Together / vLLM). |
EMBEDDING_API_KEY | Bearer key for openai_compatible or voyage providers. |
GEMINI_API_KEY | Google AI Studio API key for the gemini provider. |
CONFIDENCE_THRESHOLD | Default min_score (0-1). Tool argument has priority. |
RERANKER_API_BASE | OpenAI-compatible /rerank endpoint. Reranker is fail-soft. |
RERANKER_API_KEY | Optional bearer key for the reranker. |
RERANKER_MODEL | Reranker model id (default bge-reranker-v2-m3). |
OIDC_ISSUERS | Comma-separated OIDC issuer URLs. |
OIDC_PRESET | Convenience preset names: google,github,microsoft. |
OIDC_AUDIENCE | Expected aud claim. |
OIDC_SCOPES | Comma-separated scopes for the Protected Resource Metadata. |
OIDC_LOG_SUB_MODE | full for raw sub, otherwise SHA-256 first 12 chars (default). |
MCP_AUTH_TOKEN | **Service-to-service / CI / internal scripts only.** Use OAuth for human users. Coexists with OIDC — either method accepts. |
LEGACY_COLLECTION_COMPAT | true to allow read-only access to legacy v1 collections. Writes are still rejected. |
| Path | Purpose | Client | Authentication |
|---|---|---|---|
/mcp | MCP Protocol | Claude Desktop/Code/Mobile | ✅ |
/api/v2/* | ChromaDB REST API | Python | ✅ |
/docs | Swagger UI | Browser (API docs) | ✅ |
/openapi.json | OpenAPI Spec | API tools | ✅ |
/health | Health check | Monitoring | ❌ |
http://localhost:8080/mcp (via Caddy proxy)http://localhost:8080/healthhttp://localhost:8080/api/v2/*http://localhost:8080/docs---
Visit https://your-server.com/docs for Swagger UI documentation of all ChromaDB REST API endpoints.
---
curl -X POST https://your-server.com/mcp \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_TOKEN" \ -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
curl -X POST "https://your-server.com/mcp" \ -H "Authorization: Bearer YOUR_TOKEN" \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
curl https://your-server.com/api/v2/heartbeat \ -H "Authorization: Bearer YOUR_TOKEN"
yarn test:all ```
Unit Test Coverage:
See __tests__/README.md for detailed testing strategy.
yarn test
ChromaDB 远程 MCP 服务器概述:本项目为 ChromaDB 实例提供远程访问功能,允许所有 Claude 客户端(桌面、代码、移动)访问同一自主托管的 ChromaDB 实例。
功能特点:共享内存跨设备、自主托管和私有、远程访问、完整 ChromaDB 支持等。
环境依赖与系统要求:本项目需要 Node.js、Docker 等依赖包,系统要求包括 CPU、内存等。
安装步骤:使用 Docker Compose 或源码安装,包括下载依赖包、配置环境变量等。
使用教程:快速启动、Python 示例、Node.js 示例等。
配置说明:MCP 协议、环境变量、关键参数等。
API/接口说明:MCP 协议、ChromaDB REST API、Swagger UI 等。
工作流 / 模块说明:测试流程、模块介绍等。
FAQ 摘要:常见问题和解决方案等。
该项目提供了一个开源的MCP工具,支持ChromaDB的远程MCP服务,代码质量较高,但缺乏文档和示例。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,Chroma 向量存储 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | chromadb-remote-mcp |
| 原始描述 | 开源MCP工具:Remote MCP server for ChromaDB。⭐12 · TypeScript |
| Topics | mcpchromadbtypescript |
| GitHub | https://github.com/meloncafe/chromadb-remote-mcp |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-05-18 · 更新时间:2026-05-24 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端