# AgentFront: FrontMCP > AI Agent Infrastructure - MCP servers, secure sandboxes, vector databases, and more... ## FrontMCP - [FrontMCP / v1.7 (latest) (235 pages)](https://docs.agentfront.dev/_llms/front-mcp/v1-7-latest.md): Documentation for FrontMCP / v1.7 (latest). - [FrontMCP / v1.6 (234 pages)](https://docs.agentfront.dev/_llms/front-mcp/v1-6.md): Documentation for FrontMCP / v1.6. - [FrontMCP / v1.5 (233 pages)](https://docs.agentfront.dev/_llms/front-mcp/v1-5.md): Documentation for FrontMCP / v1.5. - [FrontMCP / v1.4 (233 pages)](https://docs.agentfront.dev/_llms/front-mcp/v1-4.md): Documentation for FrontMCP / v1.4. - [FrontMCP / v1.3 (229 pages)](https://docs.agentfront.dev/_llms/front-mcp/v1-3.md): Documentation for FrontMCP / v1.3. - [FrontMCP / v1.2 (228 pages)](https://docs.agentfront.dev/_llms/front-mcp/v1-2.md): Documentation for FrontMCP / v1.2. - [FrontMCP / v1.1 (212 pages)](https://docs.agentfront.dev/_llms/front-mcp/v1-1.md): Documentation for FrontMCP / v1.1. - [FrontMCP / v1.0 (197 pages)](https://docs.agentfront.dev/_llms/front-mcp/v1-0.md): Documentation for FrontMCP / v1.0. - [FrontMCP / v0.12 (169 pages)](https://docs.agentfront.dev/_llms/front-mcp/v0-12.md): Documentation for FrontMCP / v0.12. - [FrontMCP / v0.11 (121 pages)](https://docs.agentfront.dev/_llms/front-mcp/v0-11.md): Documentation for FrontMCP / v0.11. - [FrontMCP / v0.10 (114 pages)](https://docs.agentfront.dev/_llms/front-mcp/v0-10.md): Documentation for FrontMCP / v0.10. ### v0.9 #### Documentation ##### Get Started - [Welcome to FrontMCP](https://docs.agentfront.dev/frontmcp/v/0.9/getting-started/welcome.md): The TypeScript way to build MCP servers with decorators, DI, and Streamable HTTP. - [Installation](https://docs.agentfront.dev/frontmcp/v/0.9/getting-started/installation.md) - [Quickstart](https://docs.agentfront.dev/frontmcp/v/0.9/getting-started/quickstart.md): Build your first MCP server with FrontMCP in under 5 minutes ##### FrontMCP - [FrontMCP Overview](https://docs.agentfront.dev/frontmcp/v/0.9/fundamentals/overview.md): Core concepts and components for building FrontMCP servers ###### Core Components - [The FrontMCP Server](https://docs.agentfront.dev/frontmcp/v/0.9/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/0.9/servers/apps.md) - [Tools](https://docs.agentfront.dev/frontmcp/v/0.9/servers/tools.md) - [Resources](https://docs.agentfront.dev/frontmcp/v/0.9/servers/resources.md) - [Prompts](https://docs.agentfront.dev/frontmcp/v/0.9/servers/prompts.md) - [Agents](https://docs.agentfront.dev/frontmcp/v/0.9/servers/agents.md) - [Elicitation](https://docs.agentfront.dev/frontmcp/v/0.9/servers/elicitation.md) - [Skills](https://docs.agentfront.dev/frontmcp/v/0.9/servers/skills.md) - [Discovery APIs](https://docs.agentfront.dev/frontmcp/v/0.9/servers/discovery.md): Understand how FrontMCP answers MCP list/get flows for prompts and resources. ###### Context Classes - [Context Classes Overview](https://docs.agentfront.dev/frontmcp/v/0.9/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/0.9/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/0.9/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/0.9/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/0.9/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/0.9/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/0.9/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. ###### Authentication - [Authentication Overview](https://docs.agentfront.dev/frontmcp/v/0.9/authentication/overview.md): Understanding FrontMCP's three-tier authentication system - [Authorization Modes](https://docs.agentfront.dev/frontmcp/v/0.9/authentication/modes.md): Deep dive into public, transparent, and orchestrated authentication modes - [Local OAuth Provider](https://docs.agentfront.dev/frontmcp/v/0.9/authentication/local.md): Configure FrontMCP's built-in OAuth 2.1 authorization server - [Remote OAuth Providers](https://docs.agentfront.dev/frontmcp/v/0.9/authentication/remote.md): Connect to external identity providers like Auth0, Okta, and Azure AD - [Remote OAuth Proxy](https://docs.agentfront.dev/frontmcp/v/0.9/authentication/remote-proxy.md): Proxy authentication to IdPs without Dynamic Client Registration support - [Client ID Metadata Documents (CIMD)](https://docs.agentfront.dev/frontmcp/v/0.9/authentication/cimd.md): Self-hosting client metadata for decentralized OAuth client registration - [Progressive Authorization](https://docs.agentfront.dev/frontmcp/v/0.9/authentication/progressive.md): Implement incremental app-by-app authorization for multi-provider scenarios - [Tokens & Sessions](https://docs.agentfront.dev/frontmcp/v/0.9/authentication/token.md): Token lifecycle, session management, and storage configuration - [Production Checklist](https://docs.agentfront.dev/frontmcp/v/0.9/authentication/production.md): Security requirements and best practices for production deployment - [Authentication Demo Servers](https://docs.agentfront.dev/frontmcp/v/0.9/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/0.9/deployment/local-dev-server.md) - [Production Build](https://docs.agentfront.dev/frontmcp/v/0.9/deployment/production-build.md) - [Runtime Modes](https://docs.agentfront.dev/frontmcp/v/0.9/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/0.9/deployment/direct-client.md) - [Redis Setup](https://docs.agentfront.dev/frontmcp/v/0.9/deployment/redis-setup.md): FrontMCP uses Redis for caching, session storage, and distributed state management. - [Vercel KV](https://docs.agentfront.dev/frontmcp/v/0.9/deployment/vercel-kv.md): Use Vercel KV for edge-compatible session storage and caching - [Serverless Deployment](https://docs.agentfront.dev/frontmcp/v/0.9/deployment/serverless.md) ##### Extensibility - [Context Providers](https://docs.agentfront.dev/frontmcp/v/0.9/extensibility/providers.md) - [Context](https://docs.agentfront.dev/frontmcp/v/0.9/extensibility/request-context.md) - [Logging Transports](https://docs.agentfront.dev/frontmcp/v/0.9/extensibility/logging.md): Create and register custom log transports for FrontMCP. ###### Plugins - [Plugins Overview](https://docs.agentfront.dev/frontmcp/v/0.9/plugins/overview.md): Extend FrontMCP servers with cross-cutting capabilities using plugins - [Introduction](https://docs.agentfront.dev/frontmcp/v/0.9/plugins/introduction.md): Getting started with FrontMCP Plugins - [Creating Plugins](https://docs.agentfront.dev/frontmcp/v/0.9/plugins/creating-plugins.md): Build custom FrontMCP plugins - [Cache Plugin](https://docs.agentfront.dev/frontmcp/v/0.9/plugins/official/cache.md): Cache tool responses to improve performance and reduce external API calls. - [Remember Plugin](https://docs.agentfront.dev/frontmcp/v/0.9/plugins/official/remember.md): Give AI agents persistent memory across sessions. Remember user preferences, conversation context, and learned information. - [CodeCall Plugin](https://docs.agentfront.dev/frontmcp/v/0.9/plugins/official/codecall.md): Execute AI-generated code securely using EnclaveVM. Let AI agents write and run code within your MCP server. ###### Adapters - [Adapters Overview](https://docs.agentfront.dev/frontmcp/v/0.9/adapters/overview.md): Transform external APIs into MCP tools with FrontMCP adapters - [OpenAPI Adapter](https://docs.agentfront.dev/frontmcp/v/0.9/adapters/openapi-adapter.md): Generate MCP tools directly from an OpenAPI spec and call them with strong validation. ##### Testing - [Testing](https://docs.agentfront.dev/frontmcp/v/0.9/testing/overview.md): End-to-end testing framework for FrontMCP servers - [Test Fixtures](https://docs.agentfront.dev/frontmcp/v/0.9/testing/fixtures.md): Playwright-inspired fixture system for MCP testing - [Custom Matchers](https://docs.agentfront.dev/frontmcp/v/0.9/testing/matchers.md): MCP-specific Jest matchers for cleaner assertions - [Authentication Testing](https://docs.agentfront.dev/frontmcp/v/0.9/testing/authentication.md): Test authentication flows with JWT token generation - [Mocking & Interception](https://docs.agentfront.dev/frontmcp/v/0.9/testing/interceptors.md): Mock and intercept MCP protocol requests and responses - [HTTP Mocking](https://docs.agentfront.dev/frontmcp/v/0.9/testing/http-mocking.md): Mock external HTTP requests for offline testing - [API Reference](https://docs.agentfront.dev/frontmcp/v/0.9/testing/api-reference.md): Complete API reference for @frontmcp/testing ##### Guides - [Platform-Aware UI Library](https://docs.agentfront.dev/frontmcp/v/0.9/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/0.9/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/0.9/guides/add-openapi-adapter.md): Generate MCP tools automatically from an OpenAPI specification - [Caching & Cache Miss](https://docs.agentfront.dev/frontmcp/v/0.9/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/0.9/guides/create-plugin.md) - [Customize Flow Stages](https://docs.agentfront.dev/frontmcp/v/0.9/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/0.9/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/0.9/guides/prompts-and-resources.md): Create MCP prompts for LLM instructions and resources for data access ###### Advanced Patterns - [Role-Based Authorization](https://docs.agentfront.dev/frontmcp/v/0.9/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/0.9/guides/site-scoped-authorization.md): Implement multi-tenant authorization with site-based access control - [CodeCall CRM Demo](https://docs.agentfront.dev/frontmcp/v/0.9/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/0.9/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/0.9/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/0.9/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/0.9/guides/testing-plugins-and-hooks.md): Write E2E tests for custom plugins, hooks, and authorization logic #### SDK Reference ##### Decorators - [Decorators Overview](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/overview.md): FrontMCP uses TypeScript decorators to define MCP server components declaratively. All decorators follow a metadata-first design with Zod schema validation. - [@FrontMcp](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/frontmcp.md): The @FrontMcp decorator is the entry point for creating an MCP server. It configures the server, registers apps, and manages the server lifecycle. - [@App](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/app.md): The @App decorator defines an application module that groups related tools, resources, prompts, agents, and other components. - [@Tool](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/tool.md): The @Tool decorator defines an MCP tool with validated input/output schemas and full TypeScript type inference. - [@Resource](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/resource.md): The @Resource decorator defines a static MCP resource with a fixed URI that can be read by AI clients. - [@ResourceTemplate](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/resource-template.md): The @ResourceTemplate decorator defines a dynamic MCP resource with a URI template (RFC 6570) that extracts parameters from the requested URI. - [@Prompt](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/prompt.md): The @Prompt decorator defines an MCP prompt template that can be invoked by AI clients to generate structured prompts. - [@Agent](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/agent.md): The @Agent decorator defines an autonomous AI agent that uses an LLM to execute tasks with access to tools. - [@Skill](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/skill.md): The @Skill decorator defines a knowledge package that bundles instructions and tool references for specific workflows. - [@Provider](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/provider.md): The @Provider decorator registers a class as a dependency injection provider that can be injected into tools, resources, agents, and other components. - [@Plugin](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/plugin.md): The @Plugin decorator creates reusable modules that bundle providers, tools, resources, and context extensions. - [Flow Hooks](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/decorators/hooks.md): FrontMCP provides hook decorators for intercepting and extending flow execution. Hooks allow you to add cross-cutting concerns like logging, validation, and caching. ##### Core Classes - [FrontMcpInstance](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/core/frontmcp-instance.md): FrontMcpInstance is the main entry point for creating and managing FrontMCP servers. It provides multiple factory methods for different deployment scenarios. - [Scope](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/core/scope.md): Scope provides access to all registries and services within a FrontMCP server. It's the central point for accessing tools, resources, prompts, agents, skills, and other registered components. - [FrontMcpServer](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/core/server.md): FrontMcpServer manages the HTTP server interface for FrontMCP. It supports multiple host adapters (Express, Fastify, etc.) and both server and serverless deployments. - [DirectClient](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/core/direct-client.md): DirectClient provides programmatic access to FrontMCP servers with automatic tool formatting for different LLM platforms (OpenAI, Claude, LangChain, etc.). ##### Registries - [Registries Overview](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/overview.md): FrontMCP uses registries to manage collections of tools, resources, prompts, agents, skills, and other components. All registries follow common patterns for registration, lookup, and change events. - [ToolRegistry](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/tool-registry.md): The ToolRegistry manages all MCP tools within a scope. It provides methods for listing, finding, and subscribing to tool changes. - [ResourceRegistry](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/resource-registry.md): The ResourceRegistry manages all MCP resources within a scope, including both static resources and resource templates. - [PromptRegistry](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/prompt-registry.md): The PromptRegistry manages all MCP prompts within a scope. Prompts are reusable message templates that can be parameterized. - [AgentRegistry](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/agent-registry.md): The AgentRegistry manages all MCP agents within a scope. Agents are autonomous components that can be called as tools and have their own set of visible tools. - [SkillRegistry](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/skill-registry.md): The SkillRegistry manages all MCP skills within a scope. Skills are reusable prompts/instructions that can be searched, loaded, and optionally synced to external storage. - [PluginRegistry](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/plugin-registry.md): The PluginRegistry manages all plugins within a scope. Plugins extend FrontMCP functionality by providing tools, resources, prompts, skills, providers, and hooks. - [HookRegistry](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/hook-registry.md): The HookRegistry manages all flow hooks within a scope. Hooks intercept and extend the execution of tools, resources, and prompts at various stages. - [ProviderRegistry](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/provider-registry.md): The ProviderRegistry manages dependency injection providers within a scope. It handles provider instantiation, scoping, and lifecycle management. - [AuthRegistry](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/registries/auth-registry.md): The AuthRegistry manages authentication providers within a scope. It handles auth configuration, provider detection, and orchestration. ##### Errors - [Errors Overview](https://docs.agentfront.dev/frontmcp/v/0.9/sdk-reference/errors/overview.md): FrontMCP provides a comprehensive error hierarchy with MCP-compliant error codes for proper JSON-RPC error responses. ### v0.8 #### Documentation ##### Get Started - [Welcome to FrontMCP](https://docs.agentfront.dev/frontmcp/v/0.8/getting-started/welcome.md): The TypeScript way to build MCP servers with decorators, DI, and Streamable HTTP. - [Installation](https://docs.agentfront.dev/frontmcp/v/0.8/getting-started/installation.md) - [Quickstart](https://docs.agentfront.dev/frontmcp/v/0.8/getting-started/quickstart.md): Build your first MCP server with FrontMCP in under 5 minutes ##### FrontMCP - [FrontMCP Overview](https://docs.agentfront.dev/frontmcp/v/0.8/fundamentals/overview.md): Core concepts and components for building FrontMCP servers ###### Core Components - [The FrontMCP Server](https://docs.agentfront.dev/frontmcp/v/0.8/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/0.8/servers/apps.md) - [Tools](https://docs.agentfront.dev/frontmcp/v/0.8/servers/tools.md) - [Resources](https://docs.agentfront.dev/frontmcp/v/0.8/servers/resources.md) - [Prompts](https://docs.agentfront.dev/frontmcp/v/0.8/servers/prompts.md) - [Agents](https://docs.agentfront.dev/frontmcp/v/0.8/servers/agents.md) - [Elicitation](https://docs.agentfront.dev/frontmcp/v/0.8/servers/elicitation.md) - [Skills](https://docs.agentfront.dev/frontmcp/v/0.8/servers/skills.md) - [Discovery APIs](https://docs.agentfront.dev/frontmcp/v/0.8/servers/discovery.md): Understand how FrontMCP answers MCP list/get flows for prompts and resources. ###### Context Classes - [Context Classes Overview](https://docs.agentfront.dev/frontmcp/v/0.8/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/0.8/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/0.8/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/0.8/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/0.8/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/0.8/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/0.8/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. ###### Authentication - [Authentication Overview](https://docs.agentfront.dev/frontmcp/v/0.8/authentication/overview.md): Understanding FrontMCP's three-tier authentication system - [Authorization Modes](https://docs.agentfront.dev/frontmcp/v/0.8/authentication/modes.md): Deep dive into public, transparent, and orchestrated authentication modes - [Local OAuth Provider](https://docs.agentfront.dev/frontmcp/v/0.8/authentication/local.md): Configure FrontMCP's built-in OAuth 2.1 authorization server - [Remote OAuth Providers](https://docs.agentfront.dev/frontmcp/v/0.8/authentication/remote.md): Connect to external identity providers like Auth0, Okta, and Azure AD - [Remote OAuth Proxy](https://docs.agentfront.dev/frontmcp/v/0.8/authentication/remote-proxy.md): Proxy authentication to IdPs without Dynamic Client Registration support - [Client ID Metadata Documents (CIMD)](https://docs.agentfront.dev/frontmcp/v/0.8/authentication/cimd.md): Self-hosting client metadata for decentralized OAuth client registration - [Progressive Authorization](https://docs.agentfront.dev/frontmcp/v/0.8/authentication/progressive.md): Implement incremental app-by-app authorization for multi-provider scenarios - [Tokens & Sessions](https://docs.agentfront.dev/frontmcp/v/0.8/authentication/token.md): Token lifecycle, session management, and storage configuration - [Production Checklist](https://docs.agentfront.dev/frontmcp/v/0.8/authentication/production.md): Security requirements and best practices for production deployment - [Authentication Demo Servers](https://docs.agentfront.dev/frontmcp/v/0.8/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/0.8/deployment/local-dev-server.md) - [Production Build](https://docs.agentfront.dev/frontmcp/v/0.8/deployment/production-build.md) - [Runtime Modes](https://docs.agentfront.dev/frontmcp/v/0.8/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/0.8/deployment/direct-client.md) - [Redis Setup](https://docs.agentfront.dev/frontmcp/v/0.8/deployment/redis-setup.md): FrontMCP uses Redis for caching, session storage, and distributed state management. - [Vercel KV](https://docs.agentfront.dev/frontmcp/v/0.8/deployment/vercel-kv.md): Use Vercel KV for edge-compatible session storage and caching - [Serverless Deployment](https://docs.agentfront.dev/frontmcp/v/0.8/deployment/serverless.md) ##### Extensibility - [Context Providers](https://docs.agentfront.dev/frontmcp/v/0.8/extensibility/providers.md) - [Context](https://docs.agentfront.dev/frontmcp/v/0.8/extensibility/request-context.md) - [Logging Transports](https://docs.agentfront.dev/frontmcp/v/0.8/extensibility/logging.md): Create and register custom log transports for FrontMCP. ###### Plugins - [Plugins Overview](https://docs.agentfront.dev/frontmcp/v/0.8/plugins/overview.md): Extend FrontMCP servers with cross-cutting capabilities using plugins - [Introduction](https://docs.agentfront.dev/frontmcp/v/0.8/plugins/introduction.md): Getting started with FrontMCP Plugins - [Creating Plugins](https://docs.agentfront.dev/frontmcp/v/0.8/plugins/creating-plugins.md): Build custom FrontMCP plugins - [Cache Plugin](https://docs.agentfront.dev/frontmcp/v/0.8/plugins/official/cache.md): Cache tool responses to improve performance and reduce external API calls. - [Remember Plugin](https://docs.agentfront.dev/frontmcp/v/0.8/plugins/official/remember.md): Give AI agents persistent memory across sessions. Remember user preferences, conversation context, and learned information. - [CodeCall Plugin](https://docs.agentfront.dev/frontmcp/v/0.8/plugins/official/codecall.md): Execute AI-generated code securely using EnclaveVM. Let AI agents write and run code within your MCP server. ###### Adapters - [Adapters Overview](https://docs.agentfront.dev/frontmcp/v/0.8/adapters/overview.md): Transform external APIs into MCP tools with FrontMCP adapters - [OpenAPI Adapter](https://docs.agentfront.dev/frontmcp/v/0.8/adapters/openapi-adapter.md): Generate MCP tools directly from an OpenAPI spec and call them with strong validation. ##### Testing - [Testing](https://docs.agentfront.dev/frontmcp/v/0.8/testing/overview.md): End-to-end testing framework for FrontMCP servers - [Test Fixtures](https://docs.agentfront.dev/frontmcp/v/0.8/testing/fixtures.md): Playwright-inspired fixture system for MCP testing - [Custom Matchers](https://docs.agentfront.dev/frontmcp/v/0.8/testing/matchers.md): MCP-specific Jest matchers for cleaner assertions - [Authentication Testing](https://docs.agentfront.dev/frontmcp/v/0.8/testing/authentication.md): Test authentication flows with JWT token generation - [Mocking & Interception](https://docs.agentfront.dev/frontmcp/v/0.8/testing/interceptors.md): Mock and intercept MCP protocol requests and responses - [HTTP Mocking](https://docs.agentfront.dev/frontmcp/v/0.8/testing/http-mocking.md): Mock external HTTP requests for offline testing - [API Reference](https://docs.agentfront.dev/frontmcp/v/0.8/testing/api-reference.md): Complete API reference for @frontmcp/testing ##### Guides - [Platform-Aware UI Library](https://docs.agentfront.dev/frontmcp/v/0.8/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/0.8/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/0.8/guides/add-openapi-adapter.md): Generate MCP tools automatically from an OpenAPI specification - [Caching & Cache Miss](https://docs.agentfront.dev/frontmcp/v/0.8/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/0.8/guides/create-plugin.md) - [Customize Flow Stages](https://docs.agentfront.dev/frontmcp/v/0.8/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/0.8/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/0.8/guides/prompts-and-resources.md): Create MCP prompts for LLM instructions and resources for data access ###### Advanced Patterns - [Role-Based Authorization](https://docs.agentfront.dev/frontmcp/v/0.8/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/0.8/guides/site-scoped-authorization.md): Implement multi-tenant authorization with site-based access control - [CodeCall CRM Demo](https://docs.agentfront.dev/frontmcp/v/0.8/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/0.8/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/0.8/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/0.8/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/0.8/guides/testing-plugins-and-hooks.md): Write E2E tests for custom plugins, hooks, and authorization logic #### SDK Reference ##### Decorators - [Decorators Overview](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/overview.md): FrontMCP uses TypeScript decorators to define MCP server components declaratively. All decorators follow a metadata-first design with Zod schema validation. - [@FrontMcp](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/frontmcp.md): The @FrontMcp decorator is the entry point for creating an MCP server. It configures the server, registers apps, and manages the server lifecycle. - [@App](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/app.md): The @App decorator defines an application module that groups related tools, resources, prompts, agents, and other components. - [@Tool](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/tool.md): The @Tool decorator defines an MCP tool with validated input/output schemas and full TypeScript type inference. - [@Resource](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/resource.md): The @Resource decorator defines a static MCP resource with a fixed URI that can be read by AI clients. - [@ResourceTemplate](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/resource-template.md): The @ResourceTemplate decorator defines a dynamic MCP resource with a URI template (RFC 6570) that extracts parameters from the requested URI. - [@Prompt](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/prompt.md): The @Prompt decorator defines an MCP prompt template that can be invoked by AI clients to generate structured prompts. - [@Agent](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/agent.md): The @Agent decorator defines an autonomous AI agent that uses an LLM to execute tasks with access to tools. - [@Skill](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/skill.md): The @Skill decorator defines a knowledge package that bundles instructions and tool references for specific workflows. - [@Provider](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/provider.md): The @Provider decorator registers a class as a dependency injection provider that can be injected into tools, resources, agents, and other components. - [@Plugin](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/plugin.md): The @Plugin decorator creates reusable modules that bundle providers, tools, resources, and context extensions. - [Flow Hooks](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/decorators/hooks.md): FrontMCP provides hook decorators for intercepting and extending flow execution. Hooks allow you to add cross-cutting concerns like logging, validation, and caching. ##### Core Classes - [FrontMcpInstance](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/core/frontmcp-instance.md): FrontMcpInstance is the main entry point for creating and managing FrontMCP servers. It provides multiple factory methods for different deployment scenarios. - [Scope](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/core/scope.md): Scope provides access to all registries and services within a FrontMCP server. It's the central point for accessing tools, resources, prompts, agents, skills, and other registered components. - [FrontMcpServer](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/core/server.md): FrontMcpServer manages the HTTP server interface for FrontMCP. It supports multiple host adapters (Express, Fastify, etc.) and both server and serverless deployments. - [DirectClient](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/core/direct-client.md): DirectClient provides programmatic access to FrontMCP servers with automatic tool formatting for different LLM platforms (OpenAI, Claude, LangChain, etc.). ##### Registries - [Registries Overview](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/overview.md): FrontMCP uses registries to manage collections of tools, resources, prompts, agents, skills, and other components. All registries follow common patterns for registration, lookup, and change events. - [ToolRegistry](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/tool-registry.md): The ToolRegistry manages all MCP tools within a scope. It provides methods for listing, finding, and subscribing to tool changes. - [ResourceRegistry](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/resource-registry.md): The ResourceRegistry manages all MCP resources within a scope, including both static resources and resource templates. - [PromptRegistry](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/prompt-registry.md): The PromptRegistry manages all MCP prompts within a scope. Prompts are reusable message templates that can be parameterized. - [AgentRegistry](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/agent-registry.md): The AgentRegistry manages all MCP agents within a scope. Agents are autonomous components that can be called as tools and have their own set of visible tools. - [SkillRegistry](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/skill-registry.md): The SkillRegistry manages all MCP skills within a scope. Skills are reusable prompts/instructions that can be searched, loaded, and optionally synced to external storage. - [PluginRegistry](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/plugin-registry.md): The PluginRegistry manages all plugins within a scope. Plugins extend FrontMCP functionality by providing tools, resources, prompts, skills, providers, and hooks. - [HookRegistry](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/hook-registry.md): The HookRegistry manages all flow hooks within a scope. Hooks intercept and extend the execution of tools, resources, and prompts at various stages. - [ProviderRegistry](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/provider-registry.md): The ProviderRegistry manages dependency injection providers within a scope. It handles provider instantiation, scoping, and lifecycle management. - [AuthRegistry](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/registries/auth-registry.md): The AuthRegistry manages authentication providers within a scope. It handles auth configuration, provider detection, and orchestration. ##### Errors - [Errors Overview](https://docs.agentfront.dev/frontmcp/v/0.8/sdk-reference/errors/overview.md): FrontMCP provides a comprehensive error hierarchy with MCP-compliant error codes for proper JSON-RPC error responses. ### v0.7 #### Documentation ##### Get Started - [Welcome to FrontMCP](https://docs.agentfront.dev/frontmcp/v/0.7/getting-started/welcome.md): The TypeScript way to build MCP servers with decorators, DI, and Streamable HTTP. - [Installation](https://docs.agentfront.dev/frontmcp/v/0.7/getting-started/installation.md) - [Quickstart](https://docs.agentfront.dev/frontmcp/v/0.7/getting-started/quickstart.md): Build your first MCP server with FrontMCP in under 5 minutes - [Updates](https://docs.agentfront.dev/frontmcp/updates.md): Changelog and release history for FrontMCP ##### Servers - [The FrontMCP Server](https://docs.agentfront.dev/frontmcp/v/0.7/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/0.7/servers/apps.md) - [Tools](https://docs.agentfront.dev/frontmcp/v/0.7/servers/tools.md) - [Resources](https://docs.agentfront.dev/frontmcp/v/0.7/servers/resources.md) - [Prompts](https://docs.agentfront.dev/frontmcp/v/0.7/servers/prompts.md) - [Agents](https://docs.agentfront.dev/frontmcp/v/0.7/servers/agents.md) - [Discovery APIs](https://docs.agentfront.dev/frontmcp/v/0.7/servers/discovery.md): Understand how FrontMCP answers MCP list/get flows for prompts and resources. ##### Authentication - [Authentication Overview](https://docs.agentfront.dev/frontmcp/v/0.7/authentication/overview.md): Understanding FrontMCP's three-tier authentication system - [Authorization Modes](https://docs.agentfront.dev/frontmcp/v/0.7/authentication/modes.md): Deep dive into public, transparent, and orchestrated authentication modes - [Local OAuth Provider](https://docs.agentfront.dev/frontmcp/v/0.7/authentication/local.md): Configure FrontMCP's built-in OAuth 2.1 authorization server - [Remote OAuth Providers](https://docs.agentfront.dev/frontmcp/v/0.7/authentication/remote.md): Connect to external identity providers like Auth0, Okta, and Azure AD - [Remote OAuth Proxy](https://docs.agentfront.dev/frontmcp/v/0.7/authentication/remote-proxy.md): Proxy authentication to IdPs without Dynamic Client Registration support - [Progressive Authorization](https://docs.agentfront.dev/frontmcp/v/0.7/authentication/progressive.md): Implement incremental app-by-app authorization for multi-provider scenarios - [Tokens & Sessions](https://docs.agentfront.dev/frontmcp/v/0.7/authentication/token.md): Token lifecycle, session management, and storage configuration - [Production Checklist](https://docs.agentfront.dev/frontmcp/v/0.7/authentication/production.md): Security requirements and best practices for production deployment - [Authentication Demo Servers](https://docs.agentfront.dev/frontmcp/v/0.7/authentication/demo-servers.md): Run the Nx sample servers that showcase public, transparent, and orchestrated authentication modes. ##### Extensibility - [Context Providers](https://docs.agentfront.dev/frontmcp/v/0.7/extensibility/providers.md) - [Environment Configuration](https://docs.agentfront.dev/frontmcp/v/0.7/extensibility/config.md): Environment variable management with typed access via ConfigPlugin - [Context](https://docs.agentfront.dev/frontmcp/v/0.7/extensibility/request-context.md) - [Plugin Extensions](https://docs.agentfront.dev/frontmcp/v/0.7/extensibility/plugins.md) - [Adapters Transformers](https://docs.agentfront.dev/frontmcp/v/0.7/extensibility/adapters.md) - [Logging Transports](https://docs.agentfront.dev/frontmcp/v/0.7/extensibility/logging.md): Create and register custom log transports for FrontMCP. ##### Adapters - [Adapters Overview](https://docs.agentfront.dev/frontmcp/v/0.7/adapters/overview.md): Transform external APIs into MCP tools with FrontMCP adapters - [OpenAPI Adapter](https://docs.agentfront.dev/frontmcp/v/0.7/adapters/openapi-adapter.md): Generate MCP tools directly from an OpenAPI spec and call them with strong validation. ##### Plugins - [Plugins Overview](https://docs.agentfront.dev/frontmcp/v/0.7/plugins/overview.md): Extend FrontMCP servers with cross-cutting capabilities using plugins - [Cache Plugin](https://docs.agentfront.dev/frontmcp/v/0.7/plugins/cache-plugin.md): Transparently cache tool responses to reduce redundant computation and improve response times. - [Remember Plugin](https://docs.agentfront.dev/frontmcp/v/0.7/plugins/remember-plugin.md): Encrypted session memory with scoped storage for AI agent interactions. ###### CodeCall - [CodeCall Plugin](https://docs.agentfront.dev/frontmcp/v/0.7/plugins/codecall/overview.md): The next generation of MCP servers - orchestrate hundreds of tools through code instead of flooding the context window. - [Security Model](https://docs.agentfront.dev/frontmcp/v/0.7/plugins/codecall/security.md): Defense-in-depth security with AST validation, code transformation, runtime sandboxing, and output sanitization. - [API Reference](https://docs.agentfront.dev/frontmcp/v/0.7/plugins/codecall/api-reference.md): Complete reference for CodeCall meta-tools - search, describe, execute, and invoke. - [Configuration](https://docs.agentfront.dev/frontmcp/v/0.7/plugins/codecall/configuration.md): Complete configuration reference for CodeCall plugin - modes, VM presets, embedding strategies, and per-tool metadata. - [Production & Scaling](https://docs.agentfront.dev/frontmcp/v/0.7/plugins/codecall/scaling.md): Deploy CodeCall at scale - performance tuning, monitoring, multi-instance deployments, and operational best practices. ##### Testing - [Testing](https://docs.agentfront.dev/frontmcp/v/0.7/testing/overview.md): End-to-end testing framework for FrontMCP servers - [Test Fixtures](https://docs.agentfront.dev/frontmcp/v/0.7/testing/fixtures.md): Playwright-inspired fixture system for MCP testing - [Custom Matchers](https://docs.agentfront.dev/frontmcp/v/0.7/testing/matchers.md): MCP-specific Jest matchers for cleaner assertions - [Authentication Testing](https://docs.agentfront.dev/frontmcp/v/0.7/testing/authentication.md): Test authentication flows with JWT token generation - [Mocking & Interception](https://docs.agentfront.dev/frontmcp/v/0.7/testing/interceptors.md): Mock and intercept MCP protocol requests and responses - [HTTP Mocking](https://docs.agentfront.dev/frontmcp/v/0.7/testing/http-mocking.md): Mock external HTTP requests for offline testing - [API Reference](https://docs.agentfront.dev/frontmcp/v/0.7/testing/api-reference.md): Complete API reference for @frontmcp/testing ##### Guides - [AST Validation with ast-guard](https://docs.agentfront.dev/frontmcp/v/0.7/guides/ast-guard.md): Bank-grade JavaScript AST validation with extensible rules, presets, and the AgentScript language for safe LLM code execution. - [Secure Code Execution with Enclave](https://docs.agentfront.dev/frontmcp/v/0.7/guides/enclave.md): Execute untrusted JavaScript safely using Enclave's defense-in-depth security model combining AST validation, code transformation, and runtime sandboxing. - [Semantic Search with VectoriaDB](https://docs.agentfront.dev/frontmcp/v/0.7/guides/vectoriadb.md): Index your FrontMCP tools with VectoriaDB for offline semantic discovery and personalized tool recommendations. - [Platform-Aware UI Library](https://docs.agentfront.dev/frontmcp/v/0.7/guides/ui-library.md): Ship HTML-first consent, status, and orchestration screens with @frontmcp/ui and @frontmcp/uipack. ##### Deployment - [Local Dev Server](https://docs.agentfront.dev/frontmcp/v/0.7/deployment/local-dev-server.md) - [Production Build](https://docs.agentfront.dev/frontmcp/v/0.7/deployment/production-build.md) - [Redis Setup](https://docs.agentfront.dev/frontmcp/v/0.7/deployment/redis-setup.md): FrontMCP uses Redis for caching, session storage, and distributed state management. - [Vercel KV](https://docs.agentfront.dev/frontmcp/v/0.7/deployment/vercel-kv.md): Use Vercel KV for edge-compatible session storage and caching - [Serverless Deployment](https://docs.agentfront.dev/frontmcp/v/0.7/deployment/serverless.md)