如何安装 Code Rag？

在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式，而不是 PlugMCP 代理。

Code Rag 需要 API 密钥吗？

此记录未列出必需的环境变量。

Code Rag 使用哪种传输方式？

Code Rag 通过 stdio 在本地运行。

Code Rag MCP 服务器 | PlugMCP

Go 1.22+
```
brew install go
```

Qdrant (Vector Database)

docker run -d --name qdrant \
  -p 6333:6333 -p 6334:6334 \
  -v $(pwd)/qdrant_data:/qdrant/storage \
  qdrant/qdrant

LM Studio with an embedding model
- Download: https://lmstudio.ai
- Load model: nomic-ai/nomic-embed-text-v1.5-GGUF
- Start local server on port 1234

# 1. Clone the repo
git clone <your-repo>
cd code-rag-mcp

# 2. Install dependencies
go mod download

# 3. Build
go build -o code-rag-mcp

# 4. Configure
cp config.yaml ~/.config/code-rag-mcp/config.yaml
# Edit config.yaml with your code paths

# 5. Install globally (optional)
sudo cp code-rag-mcp /usr/local/bin/

embedding_type: "local"
embedding_model: "nomic-ai/nomic-embed-text-v1.5-GGUF"
embedding_base_url: "http://localhost:1234/v1"
embedding_dim: 768

code_paths:
  - "/Users/you/projects"  # Your code directory

{
  "mcpServers": {
    "code-rag": {
      "command": "/usr/local/bin/code-rag-mcp",
      "env": {
        "LM_STUDIO_URL": "http://localhost:1234/v1"
      }
    }
  }
}

# Add the code-rag MCP server
claude mcp add code-rag \
  --type stdio \
  --command /usr/local/bin/code-rag-mcp \
  --scope user

# Verify installation
claude mcp list
claude mcp get code-rag

{
  "mcpServers": {
    "code-rag": {
      "command": "/usr/local/bin/code-rag-mcp",
      "env": {
        "LM_STUDIO_URL": "http://localhost:1234/v1"
      }
    }
  }
}

# 1. Install the binary
sudo cp code-rag-mcp /usr/local/bin/
sudo chmod +x /usr/local/bin/code-rag-mcp

# 2. Add to Claude Code
claude mcp add code-rag \
  --type stdio \
  --command /usr/local/bin/code-rag-mcp \
  --scope user \
  --env LM_STUDIO_URL=http://localhost:1234/v1

# 3. Verify
claude mcp list

{
  "context_servers": {
    "code-rag": {
      "source": "custom",
      "command": {
        "path": "/usr/local/bin/code-rag-mcp",
        "args": [],
        "env": {
          "LM_STUDIO_URL": "http://localhost:1234/v1"
        }
      }
    }
  }
}

# 1. Install the binary (if not already done)
sudo cp code-rag-mcp /usr/local/bin/
sudo chmod +x /usr/local/bin/code-rag-mcp

# 2. Add configuration to Zed
cat << 'EOF' >> ~/.config/zed/settings.json
{
  "context_servers": {
    "code-rag": {
      "source": "custom",
      "command": {
        "path": "/usr/local/bin/code-rag-mcp",
        "args": [],
        "env": {
          "LM_STUDIO_URL": "http://localhost:1234/v1"
        }
      }
    }
  }
}
EOF

# 3. Restart Zed

# Terminal 1: Qdrant
docker start qdrant

# Terminal 2: LM Studio
# Open LM Studio UI and start the server

# Terminal 3: Test the server
./code-rag-mcp

Claude: Hi! Let me check the index status.
[Calls: get_index_stats]

You: Index my Terraform project
Claude: [Calls: index_codebase /path/to/terraform]

You: Where is the VPC configuration?
Claude: [Calls: semantic_code_search "VPC network configuration"]

"authentication middleware"
"database connection logic"
"error handling patterns"
"terraform AWS VPC modules"
"API rate limiting"

"Find code similar to: func (s *Server) HandleAuth()"

"Explain handlers/auth.go with related dependencies"

{
  "query": "authentication logic",
  "limit": 5,
  "min_score": 0.7,
  "language": "go"
}

{
  "code_snippet": "func HandleError(err error) { ... }",
  "limit": 5
}

{
  "file_path": "/path/to/file.go",
  "focus": "dependencies"
}

{
  "path": "/Users/you/projects/myapp",
  "extensions": [".go", ".py"]
}

# Test embeddings
go run scripts/test_embeddings.go

# Test indexing
go run scripts/test_indexing.go /path/to/code

# Test searches
go run scripts/test_search.go "authentication"

Model	RAM	Dim	Quality	Usage
nomic-embed-v1.5 (Q8)	548MB	768	⭐⭐⭐⭐⭐	Recommended
bge-small-en-v1.5	133MB	384	⭐⭐⭐⭐	Lightweight
all-MiniLM-L6-v2	90MB	384	⭐⭐⭐	Fast

# Check index
get_index_stats

# Re-index
index_codebase /path/to/code

# Lower minimum score
semantic_code_search "query" min_score=0.5

# Check if LM Studio is running
curl http://localhost:1234/v1/models

# Check logs
./code-rag-mcp --config config.yaml

# Restart Qdrant
docker restart qdrant

# Check logs
docker logs qdrant

Code Rag

Q: Code Rag 需要 API 密钥吗？

此记录未列出必需的环境变量。

Q: Code Rag 上次检查是什么时候？

上次检查时间：2026-10-28。 MCP (Model Context Protocol) server for semantic code search. Replace grep/ripgrep with understanding-based code search.

Mirrdhyn5 个星标

MCP (Model Context Protocol) server for semantic code search. Replace grep/ripgrep with understanding-based code search.

Knowledge Memory

安装在 PlugMCP 上运行认领此服务器

GitHub

在 PlugMCP 上运行

1# Code Rag

README.mdMCP 服务器

传输方式: stdio
状态: 本地

添加此服务器

用我们的密钥与日志托管一份副本。

服务器信息

文档

Code RAG MCP Server

🚀 Features

📋 Prerequisites

🔧 Installation

⚙️ Configuration

1. Config.yaml

2. Claude Desktop

3. Claude Code

4. Zed

🎯 Usage

1. Start services

2. Use in Claude

3. Example queries

🔍 Available MCP Tools

semantic_code_search

find_similar_code

explain_code_with_context

index_codebase

get_index_stats

🧪 Tests

📊 Recommended Embedding Models

Download in LM Studio

🐛 Troubleshooting

No results

LM Studio connection fails

Qdrant not responding

📚 Documentation

🤝 Contributing

📄 License

🙏 Acknowledgments

工具

问题

如何安装 Code Rag？

Code Rag 需要 API 密钥吗？

Code Rag 使用哪种传输方式？

Code Rag 上次检查是什么时候？

`semantic_code_search`

`find_similar_code`

`explain_code_with_context`

`index_codebase`

`get_index_stats`