# AgentFront: FrontMCP v1.1 Documentation

> AI Agent Infrastructure - MCP servers, secure sandboxes, vector databases, and more...

## Documentation

### Get Started

- [Welcome to FrontMCP](https://docs.agentfront.dev/frontmcp/v/1.1/getting-started/welcome.md): The TypeScript way to build MCP servers with decorators, DI, and Streamable HTTP.
- [Installation](https://docs.agentfront.dev/frontmcp/v/1.1/getting-started/installation.md)
- [Quickstart](https://docs.agentfront.dev/frontmcp/v/1.1/getting-started/quickstart.md): Build your first MCP server with FrontMCP in under 5 minutes
- [CLI Reference](https://docs.agentfront.dev/frontmcp/v/1.1/getting-started/cli-reference.md): Complete reference for all FrontMCP CLI commands

### FrontMCP

- [FrontMCP Overview](https://docs.agentfront.dev/frontmcp/v/1.1/fundamentals/overview.md): Core concepts and components for building FrontMCP servers
- [Schemas — lazy by default](https://docs.agentfront.dev/frontmcp/v/1.1/fundamentals/schemas.md): FrontMCP re-exports Zod via `@frontmcp/sdk` as a lazy-by-default Proxy — ~50× faster cold start with identical API.

#### Core Components

- [The FrontMCP Server](https://docs.agentfront.dev/frontmcp/v/1.1/servers/server.md): The core FrontMCP server — start with the minimum and scale up with HTTP, sessions, logging, providers, and authentication.
- [Apps](https://docs.agentfront.dev/frontmcp/v/1.1/servers/apps.md)
- [Tools](https://docs.agentfront.dev/frontmcp/v/1.1/servers/tools.md)
- [Resources](https://docs.agentfront.dev/frontmcp/v/1.1/servers/resources.md)
- [Prompts](https://docs.agentfront.dev/frontmcp/v/1.1/servers/prompts.md)
- [Agents](https://docs.agentfront.dev/frontmcp/v/1.1/servers/agents.md)
- [Elicitation](https://docs.agentfront.dev/frontmcp/v/1.1/servers/elicitation.md)
- [Skills](https://docs.agentfront.dev/frontmcp/v/1.1/servers/skills.md)
- [Discovery APIs](https://docs.agentfront.dev/frontmcp/v/1.1/servers/discovery.md): Understand how FrontMCP answers MCP list/get flows for prompts and resources.
- [ESM Packages](https://docs.agentfront.dev/frontmcp/v/1.1/servers/esm-packages.md): Load npm packages at runtime as MCP apps with caching, auto-update, and private registry support
- [Flows](https://docs.agentfront.dev/frontmcp/v/1.1/servers/flows.md): Named execution pipelines with lifecycle stages for request processing
- [Jobs](https://docs.agentfront.dev/frontmcp/v/1.1/servers/jobs.md)
- [Workflows](https://docs.agentfront.dev/frontmcp/v/1.1/servers/workflows.md)
- [Channels](https://docs.agentfront.dev/frontmcp/v/1.1/servers/channels.md)
- [Guard](https://docs.agentfront.dev/frontmcp/v/1.1/servers/guard.md): Rate limiting, concurrency control, execution timeout, and IP filtering for FrontMCP tools and agents.

#### Context Classes

- [Context Classes Overview](https://docs.agentfront.dev/frontmcp/v/1.1/sdk-reference/contexts/overview.md): FrontMCP provides context classes that serve as the base for all entry types (tools, resources, prompts, agents, skills). These classes provide access to dependency injection, logging, authentication, and other services.
- [ExecutionContextBase](https://docs.agentfront.dev/frontmcp/v/1.1/sdk-reference/contexts/execution-context-base.md): ExecutionContextBase is the abstract base class that provides common functionality for all entry context classes (ToolContext, ResourceContext, AgentContext, SkillContext).
- [ToolContext](https://docs.agentfront.dev/frontmcp/v/1.1/sdk-reference/contexts/tool-context.md): ToolContext is the base class for all tool implementations. It extends ExecutionContextBase and provides tool-specific features like notifications, progress reporting, and elicitation.
- [ResourceContext](https://docs.agentfront.dev/frontmcp/v/1.1/sdk-reference/contexts/resource-context.md): ResourceContext is the base class for all resource implementations. It extends ExecutionContextBase and provides resource-specific features like URI handling and parameter extraction.
- [PromptContext](https://docs.agentfront.dev/frontmcp/v/1.1/sdk-reference/contexts/prompt-context.md): PromptContext is the base class for all prompt implementations. It provides access to prompt arguments and methods for building prompt responses.
- [AgentContext](https://docs.agentfront.dev/frontmcp/v/1.1/sdk-reference/contexts/agent-context.md): AgentContext is the base class for autonomous AI agents. It extends ExecutionContextBase and provides LLM integration, tool execution, and the default agent loop.
- [SkillContext](https://docs.agentfront.dev/frontmcp/v/1.1/sdk-reference/contexts/skill-context.md): SkillContext is the base class for skill implementations. It extends ExecutionContextBase and provides methods for loading instructions and building skill content.
- [JobContext](https://docs.agentfront.dev/frontmcp/v/1.1/sdk-reference/contexts/job-context.md): JobContext is the base class for all job implementations. It extends ExecutionContextBase and provides job-specific features like logging, progress reporting, and retry tracking.
- [ChannelContext](https://docs.agentfront.dev/frontmcp/v/1.1/sdk-reference/contexts/channel-context.md): Abstract base class for channel execution contexts. Handles incoming events and transforms them into Claude Code notifications.

#### Authentication

- [Authentication Overview](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/overview.md): Understanding FrontMCP's three-tier authentication system
- [Authorization Modes](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/modes.md): Deep dive into public, transparent, and orchestrated authentication modes
- [Local OAuth Provider](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/local.md): Configure FrontMCP's built-in OAuth 2.1 authorization server
- [Remote OAuth Providers](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/remote.md): Connect to external identity providers like Auth0, Okta, and Azure AD
- [Remote OAuth Proxy](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/remote-proxy.md): Proxy authentication to IdPs without Dynamic Client Registration support
- [Client ID Metadata Documents (CIMD)](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/cimd.md): Self-hosting client metadata for decentralized OAuth client registration
- [Progressive Authorization](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/progressive.md): Implement incremental app-by-app authorization for multi-provider scenarios
- [Tokens & Sessions](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/token.md): Token lifecycle, session management, and storage configuration
- [Production Checklist](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/production.md): Security requirements and best practices for production deployment
- [Authentication Demo Servers](https://docs.agentfront.dev/frontmcp/v/1.1/authentication/demo-servers.md): Run the Nx sample servers that showcase public, transparent, and orchestrated authentication modes.

#### Deployment

- [Local Dev Server](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/local-dev-server.md)
- [Production Build](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/production-build.md)
- [Runtime Modes](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/runtime-modes.md): Choose how to integrate FrontMCP - as an embedded SDK, HTTP server, or serverless handler
- [DirectClient](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/direct-client.md)
- [Unix Socket](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/unix-socket.md): Run FrontMCP as a persistent local server over Unix domain sockets
- [MCP Client Configuration](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/mcp-clients.md): Connect Claude Desktop, Claude Code, Cursor, and other MCP clients to your FrontMCP server
- [Serverless Deployment](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/serverless.md)
- [MCP Bundles (MCPB)](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/mcpb.md): Package a FrontMCP server as a .mcpb archive that Claude Desktop and other MCPB-aware clients can install with one click.
- [Health & Readiness Checks](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/health-checks.md): Configure /healthz and /readyz endpoints for Kubernetes, Docker, and load balancer health probing
- [High Availability & Distributed Sessions](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/high-availability.md): Deploy FrontMCP across multiple pods with heartbeat monitoring, atomic session takeover, and cross-pod notification relay
- [Configuration File](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/frontmcp-config.md): Configure FrontMCP projects with frontmcp.config.ts for multi-target builds, server settings, security headers, and HA
- [Machine ID](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/machine-id.md): Deployment-aware machine identity for session affinity, HA takeover, and distributed tracing
- [Security Headers & CSP](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/security-headers.md): Configure Content Security Policy, HSTS, and other security headers via frontmcp.config or environment variables
- [Transport Security](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/transport-security.md): Configure CORS, bind address, DNS rebinding protection, and host validation for production deployments
- [Browser Compatibility](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/browser-compatibility.md): What works in the browser and what requires Node.js

##### Storage

- [Redis Setup](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/redis-setup.md): FrontMCP uses Redis for caching, session storage, and distributed state management.
- [SQLite Setup](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/sqlite-setup.md): Use SQLite for local session, elicitation, and event storage without external infrastructure
- [Vercel KV](https://docs.agentfront.dev/frontmcp/v/1.1/deployment/vercel-kv.md): Use Vercel KV for edge-compatible session storage and caching

### Features

- [Features Overview](https://docs.agentfront.dev/frontmcp/v/1.1/features/overview.md): A quick tour of everything FrontMCP offers
- [Decorator-Driven Development](https://docs.agentfront.dev/frontmcp/v/1.1/features/decorator-driven-development.md): Build MCP servers entirely with TypeScript decorators
- [Dependency Injection](https://docs.agentfront.dev/frontmcp/v/1.1/features/dependency-injection.md): Type-safe dependency injection with @Provider and scoped containers
- [Multi-App Composition](https://docs.agentfront.dev/frontmcp/v/1.1/features/multi-app-composition.md): Compose multiple @App modules into a single MCP server
- [Authentication & Authorization](https://docs.agentfront.dev/frontmcp/v/1.1/features/authentication-and-authorization.md): Three-tier auth model from public access to full OAuth 2.1 orchestration
- [Deployment Targets](https://docs.agentfront.dev/frontmcp/v/1.1/features/deployment-targets.md): Deploy to Node.js, Vercel, AWS Lambda, or Cloudflare Workers
- [Environment Awareness](https://docs.agentfront.dev/frontmcp/v/1.1/features/environment-awareness.md): Conditionally expose tools, resources, prompts, skills, and agents based on platform, runtime, and environment
- [Plugin System](https://docs.agentfront.dev/frontmcp/v/1.1/features/plugin-system.md): Extend servers with plugins, adapters, and context extensions
- [Observability](https://docs.agentfront.dev/frontmcp/v/1.1/features/observability.md): Built-in OpenTelemetry tracing, structured logging, and per-request log collection
- [Testing Framework](https://docs.agentfront.dev/frontmcp/v/1.1/features/testing-framework.md): E2E testing with fixtures, custom matchers, and interceptors
- [Skill-Based Workflows](https://docs.agentfront.dev/frontmcp/v/1.1/features/skill-based-workflows.md): Teach AI multi-step workflows with @Skill and Agent Skills spec
- [Real-Time Channels](https://docs.agentfront.dev/frontmcp/v/1.1/features/channels.md): Push real-time notifications into Claude Code sessions with webhook, event, and chat bridge support
- [Background Tasks](https://docs.agentfront.dev/frontmcp/v/1.1/features/background-tasks.md): Durable, pollable state machines for long-running tool calls (MCP 2025-11-25 tasks spec)
- [ESM Dynamic Loading](https://docs.agentfront.dev/frontmcp/v/1.1/features/esm-dynamic-loading.md): Load npm packages at runtime as MCP apps with caching and auto-update

### Extensibility

- [Context Providers](https://docs.agentfront.dev/frontmcp/v/1.1/extensibility/providers.md)
- [Context](https://docs.agentfront.dev/frontmcp/v/1.1/extensibility/request-context.md)
- [Logging Transports](https://docs.agentfront.dev/frontmcp/v/1.1/extensibility/logging.md): Create and register custom log transports for FrontMCP.

#### Plugins

- [Plugins Overview](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/overview.md): Extend FrontMCP servers with cross-cutting capabilities using plugins
- [Creating Plugins](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/creating-plugins.md): Build custom FrontMCP plugins using the DynamicPlugin API
- [Plugin Extensions](https://docs.agentfront.dev/frontmcp/v/1.1/extensibility/plugins.md)
- [Cache Plugin](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/cache-plugin.md): Transparently cache tool responses to reduce redundant computation and improve response times.
- [Remember Plugin](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/remember-plugin.md): Encrypted session memory with scoped storage for AI agent interactions.
- [Feature Flags Plugin](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/feature-flags-plugin.md): Dynamic capability gating with Split.io, LaunchDarkly, Unleash, and custom adapters.

##### CodeCall

- [CodeCall Plugin](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/codecall/overview.md): Orchestrate hundreds of MCP tools through code instead of flooding the context window — the next generation of agentic tool management.
- [Quick Start](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/codecall/quickstart.md): Get CodeCall running in 5 minutes - from install to first execution.
- [AgentScript Guide](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/codecall/agentscript.md): Complete guide to writing AgentScript - the safe JavaScript subset used inside codecall:execute scripts.
- [API Reference](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/codecall/api-reference.md): Complete reference for CodeCall meta-tools - search, describe, execute, and invoke.
- [Configuration](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/codecall/configuration.md): Complete configuration reference for CodeCall plugin - modes, VM presets, embedding strategies, and per-tool metadata.
- [Security Model](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/codecall/security.md): Defense-in-depth security with AST validation, code transformation, runtime sandboxing, and output sanitization.
- [Production & Scaling](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/codecall/production.md): Deploy CodeCall at scale - performance tuning, monitoring, multi-instance deployments, and operational best practices.
- [Examples & Recipes](https://docs.agentfront.dev/frontmcp/v/1.1/plugins/codecall/examples.md): Real-world CodeCall patterns - CRM workflows, ETL pipelines, batch processing, and error-resilient scripts.

#### Adapters

- [Adapters Overview](https://docs.agentfront.dev/frontmcp/v/1.1/adapters/overview.md): Transform external APIs into MCP tools with FrontMCP adapters
- [OpenAPI Adapter](https://docs.agentfront.dev/frontmcp/v/1.1/adapters/openapi-adapter.md): Generate MCP tools directly from an OpenAPI spec and call them with strong validation.
- [OpenAPI Polling](https://docs.agentfront.dev/frontmcp/v/1.1/adapters/openapi-polling.md): Automatically detect OpenAPI spec changes and rebuild tools at runtime without restarts.

### Testing

- [Testing](https://docs.agentfront.dev/frontmcp/v/1.1/testing/overview.md): End-to-end testing framework for FrontMCP servers
- [Test Fixtures](https://docs.agentfront.dev/frontmcp/v/1.1/testing/fixtures.md): Playwright-inspired fixture system for MCP testing
- [Custom Matchers](https://docs.agentfront.dev/frontmcp/v/1.1/testing/matchers.md): MCP-specific Jest matchers for cleaner assertions
- [Authentication Testing](https://docs.agentfront.dev/frontmcp/v/1.1/testing/authentication.md): Test authentication flows with JWT token generation
- [Mocking & Interception](https://docs.agentfront.dev/frontmcp/v/1.1/testing/interceptors.md): Mock and intercept MCP protocol requests and responses
- [HTTP Mocking](https://docs.agentfront.dev/frontmcp/v/1.1/testing/http-mocking.md): Mock external HTTP requests for offline testing
- [API Reference](https://docs.agentfront.dev/frontmcp/v/1.1/testing/api-reference.md): Complete API reference for @frontmcp/testing

### React SDK

- [Overview](https://docs.agentfront.dev/frontmcp/v/1.1/react/overview.md): React hooks, components, and AI SDK integration for FrontMCP
- [Getting Started](https://docs.agentfront.dev/frontmcp/v/1.1/react/getting-started.md): Install @frontmcp/react, wrap your app, and make your first tool call
- [Provider & Context](https://docs.agentfront.dev/frontmcp/v/1.1/react/provider.md): FrontMcpProvider props, FrontMcpContext, and ServerRegistry
- [Hooks Reference](https://docs.agentfront.dev/frontmcp/v/1.1/react/hooks.md): Complete API reference for all @frontmcp/react hooks
- [Components](https://docs.agentfront.dev/frontmcp/v/1.1/react/components.md): Pre-built headless form and display components for @frontmcp/react
- [Dynamic Tools & Resources](https://docs.agentfront.dev/frontmcp/v/1.1/react/dynamic-tools.md): Register MCP tools and resources dynamically from React components
- [Agent Components](https://docs.agentfront.dev/frontmcp/v/1.1/react/agent-components.md): Agent-driven UI components for @frontmcp/react
- [State Management](https://docs.agentfront.dev/frontmcp/v/1.1/react/state-management.md): Expose application state as MCP resources and actions as MCP tools
- [API Client](https://docs.agentfront.dev/frontmcp/v/1.1/react/api-client.md): Register OpenAPI operations as MCP tools with pluggable HTTP clients
- [DOM Resources](https://docs.agentfront.dev/frontmcp/v/1.1/react/dom-resources.md): Read DOM elements as MCP resources for AI agent page inspection
- [AI SDK Integration](https://docs.agentfront.dev/frontmcp/v/1.1/react/ai-integration.md): Bridge MCP tools to OpenAI, Claude, Vercel AI, and LangChain
- [Router Integration](https://docs.agentfront.dev/frontmcp/v/1.1/react/router.md): Bridge React Router with MCP via useRouterBridge, navigation tools, and route resources

### Guides

- [Platform-Aware UI Library](https://docs.agentfront.dev/frontmcp/v/1.1/guides/ui-library.md): Ship HTML-first consent, status, and orchestration screens with @frontmcp/ui and @frontmcp/uipack.

#### Quick Start

- [Your First Tool](https://docs.agentfront.dev/frontmcp/v/1.1/guides/your-first-tool.md): Create your first MCP tool with FrontMCP in under 5 minutes
- [Add OpenAPI Adapter](https://docs.agentfront.dev/frontmcp/v/1.1/guides/add-openapi-adapter.md): Generate MCP tools automatically from an OpenAPI specification
- [Caching & Cache Miss](https://docs.agentfront.dev/frontmcp/v/1.1/guides/caching-and-cache-miss.md): Add transparent response caching to tools with configurable TTL and storage options

#### Building Features

- [Create Your Own Plugin](https://docs.agentfront.dev/frontmcp/v/1.1/guides/create-plugin.md)
- [Customize Flow Stages](https://docs.agentfront.dev/frontmcp/v/1.1/guides/customize-flow-stages.md): Hook into tool execution lifecycle to enforce policy, add telemetry, or transform inputs/outputs
- [Building Tool UI](https://docs.agentfront.dev/frontmcp/v/1.1/guides/building-tool-ui.md): Create rich HTML widgets for tool outputs using @frontmcp/ui components
- [Prompts and Resources](https://docs.agentfront.dev/frontmcp/v/1.1/guides/prompts-and-resources.md): Create MCP prompts for LLM instructions and resources for data access
- [Publishing ESM Packages](https://docs.agentfront.dev/frontmcp/v/1.1/guides/publishing-esm-packages.md): Create and publish npm packages that FrontMCP servers can load at runtime
- [Rate Limiting & Guards](https://docs.agentfront.dev/frontmcp/v/1.1/guides/rate-limiting-and-guards.md): Step-by-step guide to adding rate limiting, concurrency control, and IP filtering to your FrontMCP server.
- [Observability & Telemetry](https://docs.agentfront.dev/frontmcp/v/1.1/guides/observability.md): Add distributed tracing, structured logging, and vendor integrations to your FrontMCP server
- [Your First Channel](https://docs.agentfront.dev/frontmcp/v/1.1/guides/your-first-channel.md): Build a real-time notification channel that pushes events into Claude Code

#### Advanced Patterns

- [Role-Based Authorization](https://docs.agentfront.dev/frontmcp/v/1.1/guides/role-based-authorization.md): Control tool access based on user roles with a custom authorization plugin
- [Site-Scoped Authorization](https://docs.agentfront.dev/frontmcp/v/1.1/guides/site-scoped-authorization.md): Implement multi-tenant authorization with site-based access control
- [CodeCall CRM Demo](https://docs.agentfront.dev/frontmcp/v/1.1/guides/codecall-crm-demo.md): Explore the multi-tool CRM sample that showcases the CodeCall plugin in action.
- [Agent Orchestration](https://docs.agentfront.dev/frontmcp/v/1.1/guides/agents-orchestration.md): Create AI agents that can use tools autonomously with LLM providers

#### Testing

- [Testing Your First Tool](https://docs.agentfront.dev/frontmcp/v/1.1/guides/testing-your-first-tool.md): Write end-to-end tests for your FrontMCP tools using @frontmcp/testing
- [Testing OpenAPI Adapter](https://docs.agentfront.dev/frontmcp/v/1.1/guides/testing-openapi-adapter.md): Write E2E tests for OpenAPI-generated tools using HTTP mocking
- [Testing Plugins and Hooks](https://docs.agentfront.dev/frontmcp/v/1.1/guides/testing-plugins-and-hooks.md): Write E2E tests for custom plugins, hooks, and authorization logic

#### Nx Plugin

- [Nx Plugin Overview](https://docs.agentfront.dev/frontmcp/v/1.1/nx-plugin/overview.md): @frontmcp/nx — Nx generators and executors for FrontMCP monorepos
- [Monorepo Patterns](https://docs.agentfront.dev/frontmcp/v/1.1/nx-plugin/guides/monorepo-patterns.md): Architecture patterns for large FrontMCP monorepos
- [Migration from Standalone](https://docs.agentfront.dev/frontmcp/v/1.1/nx-plugin/guides/migration-from-standalone.md): Migrate a standalone FrontMCP project to an Nx monorepo