Get the FREE Ultimate OpenClaw Setup Guide →

coverity-connect

Model Context Protocol server for BlackDuck Coverity Connect static analysis platform

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio keides2-coverity-connect-mcp coverity-mcp-server \
  --env COVAUTHKEY="your_coverity_auth_key" \
  --env PROXY_HOST="" \
  --env PROXY_PASS="" \
  --env PROXY_PORT="" \
  --env PROXY_USER="" \
  --env COVAUTHUSER="your_coverity_username" \
  --env COVERITY_SSL="True" \
  --env COVERITY_HOST="your-coverity-server.com" \
  --env COVERITY_PORT="443" \
  --env COVERITY_BASE_DIR="/path/to/coverity/workspace"

How to use

This MCP server provides an AI-assisted interface to a Black Duck Coverity Connect instance. It exposes tools that let you list and explore Coverity projects and streams, perform advanced defect searches with intelligent filtering, manage users and roles, and generate security-focused analyses and quality dashboards. With natural language queries, you can ask to see high-severity defects, fetch detailed defect events, or request executive-style project health and trend reports. Available tools include search_defects for filtered defect queries, get_defect_details for defect context and remediation steps, list_projects and list_streams for project navigation, get_project_summary for health snapshots, and user-related tools like list_users and get_user_details for access control reviews. The server supports enterprise features such as SOAP API access, authentication via an auth key, proxy settings, and containerized deployment.

How to install

Prerequisites:

  • Python 3.8+ and pip
  • Git installed
  • Optional: Docker if you plan containerized deployment in future

Installation steps (recommended - direct from GitHub):

  1. Install directly from GitHub (stable path shown in README): pip install git+https://github.com/keides2/coverity-connect-mcp.git

  2. Alternatively, install from source (editable mode): git clone https://github.com/keides2/coverity-connect-mcp.git cd coverity-connect-mcp pip install -e .

Development setup (optional): git clone https://github.com/keides2/coverity-connect-mcp.git cd coverity-connect-mcp

Create and activate virtual environment

python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate

Install development dependencies

pip install -e ".[dev]"

Docker (future planned) usage (for reference): docker pull keides2/coverity-connect-mcp:latest # if published

Or build locally from source using a docker-compose.yml similar to README guidance

Additional notes

Environment variables: set COVAUTHUSER, COVAUTHKEY, COVERITY_HOST, COVERITY_PORT, and COVERITY_SSL to enable authentication and connection to Coverity Connect. Optional proxy settings (PROXY_HOST, PROXY_PORT, PROXY_USER, PROXY_PASS) may be required in corporate networks. The mcp server expects the coverity-mcp-server entry point to be available in your PATH after installation. When integrating with Claude Desktop or similar, ensure your claude_desktop_config.json references the same server name (e.g., coverity-connect) and passes the necessary environment variables. If you encounter connectivity issues, verify SSL/TLS settings and network reachability to the Coverity host and port, and confirm that the authentication keys are valid.

Related MCP Servers

Sponsor this space

Reach thousands of developers