# Hyperterse > Agentic server framework: declarative agents, MCP tools, prompts, and resources with adapters, auth, caching, and observability. ## Docs - [Model providers](https://docs.hyperterse.com/agents/model-providers.md): Configure Gemini, Vertex AI, and OpenAI-compatible providers for declarative agents. - [Overview](https://docs.hyperterse.com/agents/overview.md): How declarative agents fit into Hyperterse and how to navigate the agent guides. - [Quickstart](https://docs.hyperterse.com/agents/quickstart.md): Create your first declarative agent, run it, and stream responses. - [Runtime API](https://docs.hyperterse.com/agents/runtime-api.md): Use Hyperterse A2A v1 endpoints mounted per agent. - [Tool access](https://docs.hyperterse.com/agents/tool-access.md): Practical playbooks for choosing and rolling out agent tool permissions. - [Adapters](https://docs.hyperterse.com/concepts/adapters.md): Named database connections that tools reference for query execution. - [Authentication](https://docs.hyperterse.com/concepts/authentication.md): Tool-level authentication with built-in and custom plugins. - [Project structure](https://docs.hyperterse.com/concepts/project-structure.md): Filesystem conventions and directory layout for Hyperterse projects. - [Overview](https://docs.hyperterse.com/concepts/prompts.md): Reusable MCP prompts with arguments, interpolation, and completion hints. - [Overview](https://docs.hyperterse.com/concepts/resources.md): MCP resources and URI templates—inline content or files. - [Scripts](https://docs.hyperterse.com/concepts/scripts.md): TypeScript handlers and transforms that extend tool behavior beyond configuration. - [Tools](https://docs.hyperterse.com/concepts/tools.md): How tool definitions specify MCP tools, input schemas, and execution strategies. - [MongoDB](https://docs.hyperterse.com/databases/mongodb.md): Connect Hyperterse to MongoDB for document-backed MCP tools using native database commands. - [MySQL](https://docs.hyperterse.com/databases/mysql.md): Connect Hyperterse to MySQL for SQL-backed MCP tools with connection pooling and charset configuration. - [PostgreSQL](https://docs.hyperterse.com/databases/postgresql.md): Connect Hyperterse to PostgreSQL for SQL-backed MCP tools with connection pooling and SSL. - [Redis](https://docs.hyperterse.com/databases/redis.md): Connect Hyperterse to Redis for key-value, caching, and data structure operations. - [SQLite](https://docs.hyperterse.com/databases/sqlite.md): Connect Hyperterse to SQLite for SQL-backed MCP tools — local files, in-memory, or remote libSQL/Turso. - [AWS](https://docs.hyperterse.com/deployment/aws.md): Deploy Hyperterse on Amazon Web Services using ECS Fargate. - [Azure](https://docs.hyperterse.com/deployment/azure.md): Deploy Hyperterse on Microsoft Azure using Container Apps. - [Bare metal](https://docs.hyperterse.com/deployment/bare-metal.md): Deploy Hyperterse directly on servers without containers or orchestrators. - [Cloudflare](https://docs.hyperterse.com/deployment/cloudflare.md): Put Hyperterse behind Cloudflare for edge security, caching, and DDoS protection. - [DigitalOcean](https://docs.hyperterse.com/deployment/digital-ocean.md): Deploy Hyperterse on DigitalOcean using App Platform or Droplets. - [Docker](https://docs.hyperterse.com/deployment/docker.md): Container deployment patterns for Hyperterse — multi-stage builds, pre-built artifacts, and minimal images. - [Google Cloud](https://docs.hyperterse.com/deployment/gcp.md): Deploy Hyperterse on Google Cloud Platform using Cloud Run. - [Kubernetes](https://docs.hyperterse.com/deployment/kubernetes.md): Deploy Hyperterse on Kubernetes with health probes, resource limits, and secrets management. - [Overview](https://docs.hyperterse.com/deployment/overview.md): Build artifacts, serve from pre-compiled output, and deploy to any environment. - [Railway](https://docs.hyperterse.com/deployment/railway.md): Deploy Hyperterse on Railway with zero infrastructure management. - [Vercel](https://docs.hyperterse.com/deployment/vercel.md): Connect a Vercel-hosted frontend to a Hyperterse MCP server. - [Installation](https://docs.hyperterse.com/installation.md): Install the Hyperterse CLI—the agentic server framework for agents (A2A), MCP tools, prompts, and resources. - [Introduction](https://docs.hyperterse.com/introduction.md): The agentic server framework—agents, tools, prompts, and resources with auth, caching, and observability. - [Quickstart](https://docs.hyperterse.com/quickstart.md): The agentic server framework—docs entry points, install, run, optional MCP checks. - [Adapter](https://docs.hyperterse.com/reference/adapter-config.md): Complete field reference for adapter definition files. - [Agent](https://docs.hyperterse.com/reference/agent-config.md): Complete field reference for declarative agent definition files. - [Command line reference](https://docs.hyperterse.com/reference/cli.md): Complete command and flag reference for the Hyperterse CLI. - [Configuration schemas](https://docs.hyperterse.com/reference/configuration-schemas.md): JSON Schema files for editor-time validation of .hyperterse and .terse configuration files. - [Environment variables](https://docs.hyperterse.com/reference/environment-variables.md): Environment variables for the Hyperterse server, CLI, and `{{ env.* }}` substitution in config. - [Prompt](https://docs.hyperterse.com/reference/prompt-config.md): Complete field reference for prompt definition files. - [Resource](https://docs.hyperterse.com/reference/resource-config.md): Complete field reference for resource and resource-template definition files. - [Root](https://docs.hyperterse.com/reference/root-config.md): Complete field reference for the .hyperterse root configuration file. - [Tool](https://docs.hyperterse.com/reference/tool-config.md): Complete field reference for tool definition files. - [A2A transport](https://docs.hyperterse.com/runtime/a2a-transport.md): Per-agent A2A HTTP surface in Hyperterse—JSON-RPC, agent card, tasks, and streaming—separate from MCP. - [Caching](https://docs.hyperterse.com/runtime/caching.md): In-memory tool result caching, cache key derivation, TTL, and override behavior. - [Execution pipeline](https://docs.hyperterse.com/runtime/execution-pipeline.md): Deterministic execution flow for tool invocations from tool resolution through response serialization. - [MCP transport](https://docs.hyperterse.com/runtime/mcp-transport.md): Full MCP 2025-11-25 surface in Hyperterse, including tools, prompts, resources, completion, notifications, and session behavior. - [Observability](https://docs.hyperterse.com/runtime/observability.md): OpenTelemetry tracing and metrics, structured logging, attribute redaction, and collector integration. - [Input safety](https://docs.hyperterse.com/security/input-safety.md): Statement substitution model, security implications, and defensive patterns. - [Production hardening](https://docs.hyperterse.com/security/production-hardening.md): Security measures, deployment configuration, and hardening for production environments. ## OpenAPI Specs - [openapi](https://docs.hyperterse.com/api-reference/openapi.json)