Continue guide

You can access Snyk Studio, including Snyk's MCP server, in Continue to secure code generated with agentic workflows through an LLM. This can be achieved in several ways. When you use it for the first time, the MCP server asks for trust and trigger authentication if necessary.

Prerequisites

• Install the Continue extension

• Install the Snyk CLI

• Install the Snyk MCP

Install Continue

Add the Continue extension to your IDE. For more details, see the official Continue installation page.

Install the Snyk MCP Server in Continue

Install the Snyk MCP Server using the method that best suits your operating system and local development environment.

Install with pre-installed Snyk CLI

Create or edit the MCP configuration file ~/.continue/mcpServers/new-mcp-server.yaml .

name: MCP Server
version: 0.0.1
schema: v1
mcpServers:
  - name: Snyk
    command: /absolute/path/to/snyk
    args:
      - "mcp"
      - "-t"
      - "stdio"      
    env: {}

If the snyk command is not available, add it by following the instructions on the Installing or updating the Snyk CLI page.

Install with Node.js and npx

Create or edit the MCP configuration file ~/.continue/mcpServers/new-mcp-server.yaml .

name: MCP Server
version: 0.0.1
schema: v1
mcpServers:
  - name: Snyk
    command: npx
    args:
      - "-y"
      - "snyk@latest"
      - "mcp"
      - "-t"
      - "stdio"       
    env: {}

The following example shows a Snyk MCP Server that was successfully configured and started.

Setting up the Snyk MCP Server

The MCP Server attempts to start automatically. The following example shows a Snyk MCP Server that was successfully configured and started.

As a one-time setup, authenticate and trust the current Project directory. If required, the agentic workflow will likely manage this automatically.

If you are already authenticated with the Snyk CLI installed on your system path, or through a prior interaction, then proceed to work with the Snyk MCP Server.

Examples

Scanning for security vulnerabilities

In the chat, you can tag specific files or functions and ask Continue to scan your code for safe deployment to production.

prompt

Scan this directory for code security & dependency vulnerabilities and security issues

Continue indicates that this request is related to security vulnerability scanning and calls the Snyk MCP Server for various scans.

Continue is then able to gather all the security scanning results, both code (SAST) and dependencies (SCA), and based on recommendations and contextual information provided by the Snyk MCP Server, it is now able to provide code changes that address some or all of the security vulnerabilities that were found:

"Secure at inception" rules

To practice Secure at Inception, Snyk recommends adopting rules that align the LLM for secure code generation and workflows.

The following is a suggested instruction for creating project rules for use with Continue. Append the following contents to the rules file at .continue/rules/new-rule.md:

---
applyTo: "**"
---

# Project security best practices

- Always run **snyk_code_scan** tool for new first party code that is generated in a Snyk-supported language.
- If any security issues are found based on newly introduced or modified code or dependencies, attempt to fix the issues using the results context from **Snyk**.
- Rescan the code after fixing the issues to ensure that the issues were fixed and that there are no newly introduced issues.
- Repeat this process until no new issues are found.