Apiiro Guardian Agent

Official registry Developer tools

Apiiro Application Security Posture Management (ASPM) tools for AI coding assistants.

What can you do with Apiiro Guardian Agent?

  • Write secure code with real-time security guidance
  • Query security risks across repositories
  • Trigger differential scans on code changes
  • Analyze repository security posture
  • Manage and remediate security findings
  • Application Security Posture Management (ASPM) analysis

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code
claude mcp add --transport http apiiro-guardian-agent 'https://mcp.apiiro.com/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "apiiro-guardian-agent": {
            "type": "http",
            "url": "https://mcp.apiiro.com/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Apiiro Guardian Agent MCP Server
  2. Overview
  3. Supported Integrations
  4. Security Capabilities
  5. How It Works
  6. Setup
  7. License

Apiiro Guardian Agent MCP Server

Apiiro Guardian Agent enables AI coding assistants to leverage Application Security Posture Management (ASPM) capabilities through the Model Context Protocol (MCP). This integration allows developers to write secure code, query security risks, analyze repositories, trigger diff scans, and manage security findings directly from their AI assistant.

Overview

This MCP server connects AI assistants to Apiiro's security analysis platform, providing real-time security insights during development. The integration exposes Apiiro's security capabilities through MCP tools that can be invoked by supported AI coding assistants.

Supported Integrations

Cursor Plugin
  1. Open Cursor Settings > Tools & Integrations > MCP Tools
  2. Add a new MCP server with the URL: https://mcp.apiiro.com/mcp
Google Gemini Extension

The Gemini extension is configured through gemini-extension.json and provides access to Apiiro's security analysis tools within the Gemini CLI environment.

Configuration:

  • Extension manifest: gemini-extension.json
  • Server endpoint: https://mcp.apiiro.com/mcp
  • Authentication: OAuth, optional $APIIRO_API_TOKEN bearer token

Security Capabilities

The integration provides access to:

  • Write secure code with real-time security guidance
  • Query security risks across repositories
  • Trigger differential scans on code changes
  • Analyze repository security posture
  • Manage and remediate security findings
  • Application Security Posture Management (ASPM) analysis

How It Works

The Apiiro MCP server acts as a bridge between AI coding assistants and the Apiiro security platform. When invoked through MCP tools, the server communicates with Apiiro's API to retrieve security analysis, trigger scans, and provide actionable security insights within the developer workflow.

Setup

To use the Apiiro Guardian Agent, you need:

  1. An Apiiro account with API access
  2. A supported AI assistant configured to use MCP servers

License

Apache License 2.0

Frequently asked questions

What is Apiiro Guardian Agent?

Apiiro Application Security Posture Management (ASPM) tools for AI coding assistants.

How do I install Apiiro Guardian Agent?

It runs as a remote server. In Claude Code: claude mcp add --transport http apiiro-guardian-agent 'https://mcp.apiiro.com/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Apiiro Guardian Agent need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Apiiro Guardian Agent open source?

Yes. Its code is on GitHub under the Apache-2.0 license.

Who maintains Apiiro Guardian Agent?

It is published by apiiro. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.