frontmcp
Verified Safeby 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
npm run devEnvironment 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
fastmcp
Build Model Context Protocol (MCP) servers in TypeScript with features like session management, authentication (including OAuth), streaming, and type-safe tool/resource/prompt definitions.
mcp-proxy
A proxy server that translates Model Context Protocol (MCP) messages from stdio-based backend servers into streamable HTTP and Server-Sent Events (SSE) endpoints.
mcp-server-typescript
This server acts as a Model Context Protocol (MCP) gateway, enabling AI assistants to interact with DataForSEO APIs for various SEO data, including keyword research, SERP analysis, backlink monitoring, and on-page optimization.
boilerplate-mcp-server
This boilerplate provides a production-ready foundation for developing custom Model Context Protocol (MCP) servers in TypeScript to connect AI assistants with external APIs and data sources, exemplified by an IP geolocation lookup tool.