> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/v0.24.1/run-guardrailed-inference/using-fastapi-server/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server.

# Use the Guardrails API Server

> Expose guardrails through an HTTP API using the Guardrails API server.

The NeMo Guardrails library includes the Guardrails API server that exposes guardrails through an HTTP API.
This section covers how to run the server and interact with it.

#### [Overview](/run-guardrailed-inference/using-fastapi-server/overview)

The Guardrails API server is a tool for running guardrails in a secure, isolated environment.

Concept

#### [Run the Server](/run-guardrailed-inference/using-fastapi-server/run-guardrails-server)

Start the Guardrails API server, configure CORS, and enable auto-reload.

Tutorial

#### [Chat Completions](/run-guardrailed-inference/using-fastapi-server/chat-with-guardrailed-model)

Send chat requests, use streaming, and manage conversation threads.

Tutorial

#### [List Configurations](/run-guardrailed-inference/using-fastapi-server/list-guardrail-configs)

Retrieve available guardrails configurations from the server.

Reference

#### [List Models](/run-guardrailed-inference/using-fastapi-server/list-models)

Query the available LLM models from the configured provider.

Reference

#### [Actions Server](/run-guardrailed-inference/using-fastapi-server/actions-server)

Run guardrail actions in a secure, isolated environment.

Tutorial

> Expose guardrails through an HTTP API using the Guardrails API server.

## Docs

- [Overview of the NVIDIA NeMo Guardrails Library API Server](https://docs.nvidia.com/nemo/guardrails/v0.24.1/run-guardrailed-inference/using-fastapi-server/overview.md): The NVIDIA NeMo Guardrails library API server runs guardrails in a secure, isolated environment.
- [Run the Guardrails Server](https://docs.nvidia.com/nemo/guardrails/v0.24.1/run-guardrailed-inference/using-fastapi-server/run-guardrails-server.md): Start the Guardrails API server, configure CORS, and enable auto-reload.
- [Chat with Guardrailed Model](https://docs.nvidia.com/nemo/guardrails/v0.24.1/run-guardrailed-inference/using-fastapi-server/chat-with-guardrailed-model.md): Send chat requests, use streaming, and manage conversation threads.
- [List Guardrail Configurations](https://docs.nvidia.com/nemo/guardrails/v0.24.1/run-guardrailed-inference/using-fastapi-server/list-guardrail-configs.md): Retrieve available guardrails configurations from the server.
- [List Available Models](https://docs.nvidia.com/nemo/guardrails/v0.24.1/run-guardrailed-inference/using-fastapi-server/list-models.md): Query the available LLM models from the configured provider.
- [Use the Actions Server](https://docs.nvidia.com/nemo/guardrails/v0.24.1/run-guardrailed-inference/using-fastapi-server/actions-server.md): Run guardrail actions in a secure, isolated environment.