Back to Home
agentfront icon

frontmcp

Verified Safe

by agentfront

Overview

Develop and integrate third-party API services using the Model Context Protocol (MCP) framework, enabling AI models to interact with external systems through defined tools, resources, and prompts.

Installation

Run Command
npm run dev

Environment Variables

  • IDP_PROVIDER_URL
  • IDP_EXPECTED_AUDIENCE
  • PORT
  • NODE_ENV
  • MCP_SESSION_SECRET

Security Notes

The server explicitly deals with dynamic code execution via the `codecall` plugin using `enclave-vm` for sandboxing untrusted JavaScript. It also uses runtime transpilation for JSX/MDX templates (`new Function`/`eval` in `libs/ui/src/renderers/utils/transpiler.ts`) and regex validation in `json-schema-to-zod-v3` with ReDoS protection. Input sanitization (`libs/ui/src/runtime/sanitizer.ts`) and HTML escaping (`escapeHtml`) are implemented for UI components to prevent XSS. Button `href` protocols are validated to prevent `javascript:` injection. External API calls are made (e.g., fetching OpenAPI specs, JWKS), increasing the attack surface. Overall, the framework demonstrates strong security awareness and implements multiple safeguards for potentially risky operations, making it generally safe for its intended use, but demanding careful configuration in production environments, especially for the `codecall` plugin.

Similar Servers

Stats

Interest Score93
Security Score8
Cost ClassMedium
Stars124
Forks3
Last Update2025-12-04

Tags

TypeScriptMCPAPI IntegrationToolingFrameworkMonorepo