Unleash quality and security in your
AI coding assistant

MCP stands for Model Context Protocol, an open standard that allows AI models (LLMs) to interact with and use external data sources and tools, acting like a "USB-C port for AI".

The Sigrid platform analyzes source code against the world’s largest benchmark, 400+ billion lines across 300 technologies, to assign 1–5-star ratings for maintainability, security and architecture.

Exposing the Sigrid engine through an MCP server allows any LLM to: 

• Send Code – The IDE streams generated or edited snippets to the MCP server. 

• Receive Analysis – Sigrid returns JSON feedback on maintainability violations and security issues. 

• Autocorrect – The LLM uses these findings to regenerate cleaner code.

An MCP server is a way to extend the capabilities of a large language model (LLM) by supplying it with the possibility of executing external code to accomplish tasks that a single LLM model alone couldn’t.

Very simple example: Let’s assume that we want an LLM to analyze code for security vulnerabilities.
If you just ask a frontier model, like Sonnet 4, “What are the security vulnerabilities in this snippet?”, what happens is that the model will look at the code, and based on many, many similar patterns it has seen in its training process, it will combine those patterns with information about common security vulnerabilities (eg. a SQL injection) and the result will be a “stochastic assessment” of the security vulnerabilities.

While this works extremely well in a huge majority of cases, the obvious limitation is that it’s not truly deterministic. It’s all pattern-matching at a giant scale.

This is where the concept of an MCP server comes in!

What if there existed a mechanism that could: read a code snippet, send the code snippet to be analyzed by a deterministic tool, like Sigrid, and return output to the LLM, so that the LLM itself could really know the actual vulnerabilities in the code?
Well, this is exactly what we can do with our MCP server.

Sigrid integrates with AI coding assistants via the MCP protocol, enabling code quality and security checks during AI-assisted development. How and when Sigrid MCP is triggered depends on the coding assistant’s configuration, the LLM used, and user-defined rules or policies. Some assistants call Sigrid automatically for every code change, while others do so based on prompts (e.g., tagging @Sigrid).

SIG recommends Claude 4.x models for reliable MCP integration. Visibility of this interaction varies by assistant, but many display when Sigrid MCP is called during a coding session.

The MCP is integrated with AI Coding Assistants. Some IDEs are AI Coding Assistants (e.g. Windsurf, Cursor), some IDEs have plugins for AI Coding Assistants (e.g. VSCode with the Github Copilot plugin, JetBrains). Most IDEs have options today for integrating with some AI Coding Assistant and most AI Coding Assistants support MCP.

Can it connect to any IDE? this depends on the AI Coding Assistant.