MCP server

Sentrasec ships a Model Context Protocol server. Any MCP-capable agent, including Claude Code, Cursor, Codex, Windsurf, GitHub Copilot and VS Code, can use it to read findings, explain vulnerabilities and receive remediation plans and test plans. The agent makes the change and runs the tests; Sentrasec does not edit your code.

Per-client setup guides, including Codex and Windsurf, live at mcp.sentrasec.ai.

How it runs

sentrasec mcp

The server acts as the authenticated user: an agent cannot read findings you cannot read.

Authenticate once before starting:

sentrasec login

Available tools

Tool	Purpose
security.dast_scan	Run a DAST scan against a URL and return enriched findings
security.list_findings	List findings for a scan or across the workspace
security.explain	Explain a vulnerability by knowledge-graph node id
security.suggest_fix	Return remediation guidance for a finding, for the agent to apply
security.list_rules	List detection rules available in the engine
security.list_languages	List supported languages
security.issue_cert	Issue a pentest certificate for a set of scans

Tools follow the standard MCP schema. Clients discover them on connect: you ask in natural language and the agent selects the tool.

Claude Code

claude mcp add sentrasec -- sentrasec mcp

Cursor

In .cursor/mcp.json:

{
  "mcpServers": {
    "sentrasec": {
      "command": "sentrasec",
      "args": ["mcp"]
    }
  }
}

VS Code

In .vscode/mcp.json:

{
  "servers": {
    "sentrasec": {
      "type": "stdio",
      "command": "sentrasec",
      "args": ["mcp"]
    }
  }
}

GitHub Copilot

In the agent MCP configuration:

{
  "mcp": {
    "sentrasec": {
      "command": "sentrasec",
      "args": ["mcp"]
    }
  }
}

Using it

Once connected, ask the agent in plain language:

Which findings in this app need action?

Why is this finding a problem, and what does the remediation plan say to change?

Is the version of this package we use affected by any known vulnerabilities?

The agent selects the appropriate tool, Sentrasec answers from the same findings and knowledge graph as the web app and CLI, and the response arrives inline.

Scope and safety

The server exposes read and analysis operations; it does not modify your code, open pull requests or run your tests. Remediation plans and test plans are returned to the agent. The agent makes the change and runs the tests in your editor, where you review them, and a re-scan confirms the finding is gone.