Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@CodeBrain search for how user authentication is implemented"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CodeBrain（代码知识库大脑）is a local AI assistant that understands your codebase. It uses RAG (Retrieval-Augmented Generation) with a local embedding model and local LLM (Ollama/DeepSeek), exposes an MCP server for external AI tools, and provides a simple Gradio web UI.
Codebase indexing: auto-scan Python / Java / Go / JavaScript / TypeScript repositories
Semantic search: vectorize code chunks (functions, classes, modules) with sentence-transformers
Local vector DB: persist embeddings with ChromaDB
Natural-language Q&A: retrieve relevant snippets and generate answers with line-number citations
Incremental updates: re-index only changed files; optional file-system watcher
MCP server: expose codebrain_search and codebrain_status tools to Cursor / Claude Code / Cline
Web UI: chat + index project + view status
Related MCP server: Acemcp
pip install -r requirements.txtollama pull deepseek-coder:6.7b
ollama serveYou can change the model in config.yaml.
python -m codebrain index /path/to/your/codebaseAdd --watch to monitor file changes:
python -m codebrain index /path/to/your/codebase --watchpython -m codebrain ask "用户登录功能在哪个文件里实现的？"python -m codebrain webOpen http://127.0.0.1:7860.
config.yaml)project:
supported_languages:
- python
- java
- go
- javascript
- typescript
ignore_patterns:
- node_modules
- .git
- __pycache__
- .venv
- venv
- dist
- build
- target
- .idea
- .vscode
- .codebrain
- ".mypy_cache"
- ".pytest_cache"
indexer:
embedding_model: all-MiniLM-L6-v2 # sentence-transformers model
chunk_size: 512
chunk_overlap: 50
vector_store:
provider: chromadb
persist_directory: .codebrain/chroma_db
collection_name: codebrain
llm:
provider: ollama
model: deepseek-coder:6.7b
base_url: http://localhost:11434
temperature: 0.1
max_tokens: 2048
web:
host: 127.0.0.1
port: 7860
mcp:
transport: stdioSection | Option | Description |
|
| Languages to index |
|
| Glob patterns for directories/files to skip |
|
| HuggingFace sentence-transformers model name |
|
| Where ChromaDB stores vectors |
|
| Ollama model tag |
|
| Ollama server URL |
|
| Gradio server bind address |
CodeBrain implements an MCP server over stdio. Tools exposed:
codebrain_search(query, top_k=5, language="") — search the knowledge base
codebrain_status() — show index statistics
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"codebrain": {
"command": "python",
"args": ["-m", "codebrain", "mcp"],
"cwd": "/absolute/path/to/codebrain"
}
}
}Add to ~/.claude-code/settings.json:
{
"mcpServers": {
"codebrain": {
"command": "python",
"args": ["-m", "codebrain", "mcp"]
}
}
}Add to Cline MCP settings:
{
"mcpServers": {
"codebrain": {
"command": "python",
"args": ["-m", "codebrain", "mcp"],
"env": {},
"disabled": false,
"autoApprove": ["codebrain_search", "codebrain_status"]
}
}
}python -m codebrain --help
python -m codebrain index <path> [--watch]
python -m codebrain status
python -m codebrain ask "question" [--language python]
python -m codebrain web
python -m codebrain mcpcodebrain/
├── config.py # Configuration loading
├── models.py # CodeChunk / RetrievalResult dataclasses
├── indexer/
│ ├── parser.py # Python AST + regex-based parser for Java/Go/JS/TS
│ ├── embedder.py # sentence-transformers wrapper
│ ├── store.py # ChromaDB wrapper
│ ├── indexer.py # Scan / embed / upsert orchestration
│ └── watcher.py # File-system watcher for incremental updates
├── rag/
│ ├── llm.py # Ollama client
│ └── engine.py # RAG retrieval + generation
├── mcp_server/
│ └── server.py # MCP server implementation
├── web/
│ └── app.py # Gradio chat UI
└── main.py # CLI entry pointFirst indexing downloads the embedding model and may take a few minutes.
Make sure Ollama is running before using ask / web / MCP tools.
The vector store is stored locally in .codebrain/chroma_db by default.
MIT
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Enterprise code intelligence for M&A, security audits, and tech debt. Hosted server with 200k free.
Search your knowledge bases from any AI assistant using hybrid RAG.
Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/liuwanwan1/CodeBrain'
If you have feedback or need assistance with the MCP directory API, please join our Discord server