SCS

Provides semantic code search, analysis, and voice-assisted workflows for Claude Desktop via an MCP server.

typescript

GitHub Stars

typescript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "stevenjjobson-scs-mcp": {
      "command": "wsl",
      "args": [
        "bash",
        "-c",
        "cd /path/to/scs-mcp && python3 -m src.server"
      ],
      "env": {
        "CACHE_TTL": "300",
        "MAX_WORKERS": "4",
        "ENABLE_VOICE": "true",
        "PROJECT_NAME": "MyProject",
        "PROJECT_ROOT": "/path/to/your/code",
        "OPENAI_API_KEY": "YOUR_API_KEY",
        "ELEVENLABS_API_KEY": "YOUR_API_KEY",
        "ENABLE_GIT_HISTORY": "true"
      }
    }
  }
}

You run an MCP server that enables semantic code search, real-time analysis, and voice-assisted workflows for Claude Desktop and other MCP-compatible clients. It combines fast search, code intelligence tools, and orchestration features to help you explore, review, and refactor your codebases efficiently.

How to use

Configure your MCP client to connect to the SCS MCP server. You can run the server locally and point the client at the local runtime, or you can run the server in a separate environment and connect via HTTP if you have a remote endpoint. Once connected, you can perform semantic searches, run instant code reviews, analyze code complexity, inspect git history, and coordinate refactoring and migrations through the orchestration framework. Use natural language queries to search for code concepts, review specific files, or request insights such as security issues, dependency graphs, or potential refactoring opportunities.

How to install

Prerequisites: you need Node.js and Python installed on your system, plus a terminal or shell to run commands. You should also have a Git client available if you plan to clone and manage the codebase locally.

Step 1: Clone the repository and enter the project directory.

# Clone the repository
git clone https://github.com/StevenJJobson/scs-mcp.git
cd scs-mcp

Step 2: Run the installer to set up dependencies and environment. Check that the installer has execute permissions and run it.

chmod +x scripts/install.sh
./scripts/install.sh

Step 3: Configure Claude Desktop to connect to the MCP server. Add the following MCP server entry to your Claude Desktop config. You can use the provided Windows and macOS/Linux variants depending on your platform.

# Windows setup
{
  "mcpServers": {
    "scs-mcp": {
      "command": "wsl",
      "args": ["bash", "-c", "cd /path/to/scs-mcp && python3 -m src.server"]
    }
  }
}

# macOS/Linux setup
{
  "mcpServers": {
    "scs-mcp": {
      "command": "python3",
      "args": ["-m", "src.server"],
      "cwd": "/path/to/scs-mcp"
    }
  }
}

Available tools

search

Semantic code search combining meaning with keyword matching for fast, relevant results.

find_similar

Locate code patterns that are similar to a given snippet or function.

instant_review

Quick, real-time code quality reviews with actionable feedback.

analyze_symbol

Deep analysis of a code symbol to understand its usage and relationships.

git_search_history

Search through Git commit history to trace changes and detect introductions of bugs.

debt_orchestrator

Coordinate technical debt assessment and prioritization across the codebase.

generate_dependency_graph

Create dependency graphs in DOT, Mermaid, or JSON formats for visualization.

Built by

VeilStrat

AI signals for GTM teams