Click on "Deploy 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., "@code-context-mcp how does authentication work?"
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.
Make any LLM a codebase expert instantly. This MCP server provides deep code intelligence through semantic search, architecture mapping, security analysis, and smart context that fits perfectly in token windows. 90% more efficient than sending raw files. Perfect for Claude, GPT, and any LLM-powered IDE.
git clone https://github.com/RaheesAhmed/code-context-mcp.git
cd code-context-mcp
uv syncRelated MCP server: Portable MCP Toolkit
# Development mode with inspector
uv run mcp dev src/server.pyAdd to claude_desktop_config.json:
{
"mcpServers": {
"code-context": {
"command": "uv",
"args": ["run", "--directory", "/path/to/code-context-mcp", "mcp", "run", "src/server.py"]
}
}
}Tool | Description |
| Condensed map of all symbols in entire codebase |
| File content with related imports |
| Find function/class definitions |
| Import relationships for a file |
| File count, lines, language breakdown |
| Read file with optional line range |
Tool | Description |
| Find ALL places where a symbol is used |
| Auto-find relevant files for a question |
| Search code by meaning, not keywords |
Tool | Description |
| Trace callers/callees with Mermaid diagram |
| Auto-generate project layer diagram |
| Detect security, performance, quality issues |
Tool | Description |
| Token-efficient multi-file context |
| What breaks when you change a file |
| Git history - recently modified files |
| Step-by-step execution path tracing |
# See entire codebase structure
get_repo_map(project_path="/path/to/project")
# Find all usages of a function
find_usages(project_path="/path/to/project", symbol="authenticate")
# Auto-find relevant code for a question
smart_context(project_path="/path/to/project", question="how does auth work?")
# Build call graph with visualization
get_call_graph(project_path="/path/to/project", function_name="main")
# Analyze before making changes
analyze_change_impact(project_path="/path/to/project", file_path="src/core.py")
# Trace execution flow
trace_code_flow(project_path="/path/to/project", entry_point="handleRequest")Python 3.10+
MIT License - see LICENSE
This server cannot be deployed
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Codebase intelligence for AI agents — dead code, blast radius, ownership.
Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.
