Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
MCP (Model Context Protocol) server for semantic code search. Replace grep/ripgrep with understanding-based code search.
MCP (Model Context Protocol) server for semantic code search. Replace grep/ripgrep with understanding-based code search.
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
nomic-ai/nomic-embed-text-v1.5-GGUF# 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/
Edit ~/.config/code-rag-mcp/config.yaml:
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
File: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
File: ~/.config/Claude/claude_desktop_config.json (Linux)
{
"mcpServers": {
"code-rag": {
"command": "/usr/local/bin/code-rag-mcp",
"env": {
"LM_STUDIO_URL": "http://localhost:1234/v1"
}
}
}
}
After modification, fully restart Claude Desktop (Quit + relaunch).
Option A: Via CLI (Recommended) 🚀
# 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
Option B: Manual configuration
Claude Code uses the same file as Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json~/.config/Claude/claude_desktop_config.json{
"mcpServers": {
"code-rag": {
"command": "/usr/local/bin/code-rag-mcp",
"env": {
"LM_STUDIO_URL": "http://localhost:1234/v1"
}
}
}
}
Complete copy-paste command (after building):
# 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
File: ~/.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"
}
}
}
}
}
Complete copy-paste command:
# 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
Note: For Zed, you can also use the "Add Custom Server" button in the Agent Panel.
# 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"]
Semantic search:
"authentication middleware"
"database connection logic"
"error handling patterns"
"terraform AWS VPC modules"
"API rate limiting"
Similar code:
"Find code similar to: func (s *Server) HandleAuth()"
Explanation with context:
"Explain handlers/auth.go with related dependencies"
semantic_code_searchPrimary semantic search. Use instead of grep.
{
"query": "authentication logic",
"limit": 5,
"min_score": 0.7,
"language": "go"
}
find_similar_codeFind code similar to a given snippet.
{
"code_snippet": "func HandleError(err error) { ... }",
"limit": 5
}
explain_code_with_contextExplain a file with its context.
{
"file_path": "/path/to/file.go",
"focus": "dependencies"
}
index_codebaseIndex a directory. Run this first.
{
"path": "/Users/you/projects/myapp",
"extensions": [".go", ".py"]
}
get_index_statsCheck index status.
# 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"
nomic-ai/nomic-embed-text-v1.5-GGUF (Q8)# 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
Contributions are welcome! See CONTRIBUTING.md
MIT License - see LICENSE
MCP (Model Context Protocol) server for semantic code search. Replace grep/ripgrep with understanding-based code search.
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
Code Rag ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-28 MCP (Model Context Protocol) server for semantic code search. Replace grep/ripgrep with understanding-based code search.
