Perforce QAC includes an MCP server that exposes static analysis information (diagnostic details, fix guidelines, and checker documentation) to AI assistants, such as GitHub Copilot Chat, in a standardized, tool-agnostic format.
With the MCP server configured, you can ask the AI assistant to:
- List QAC diagnostics in your project using natural language, optionally filtered by file, severity, message number, or suppression status.
- Generate a fix for a specific diagnostic, either by using Fix with QAC Tools in the VS Code Problems panel or by referring to it from a list returned in the chat.
AI suggestions may contain errors, so you should review all changes carefully before applying.
To use the AI remediation feature, you will require the following:
- An active internet connection
- The latest version of Visual Studio Code (VSCode)
- The latest Perforce QAC Visual Studio Code extension (installed via VSIX file)
- MCP Servers Marketplace enabled in VS Code. You can enable this by clicking MCP Servers in the Extensions and then clicking Enable MCP Servers Marketplace
-
The P4SA MCP Server. You can find this in the QAC components folder - see Configuring the MCP Server for more information.
- A GitHub account
- GitHub Copilot or Copilot Chat Extension (installed from Visual Studio Marketplace)
- (Optional) An API key if using a custom large language model (LLM) instead of presets
- A valid Perforce QAC desktop licence for analysis and review of results is required for the MCP server to return diagnostics to the chat agent.
If you don’t see the MCP Servers panel in the Extensions side bar, click on the … at the top, then select Views > MCP Servers.
If a required licence is unavailable, the chat agent reports the licence error and no diagnostics are returned. Partial licensing (some results licensed, others not) is treated the same as no licence — the agent will refuse to proceed.
You can use any LLM, but Claude Sonnet 4.6 and GPT-5.3-Codex produced the best results in our testing.