Create an agent

This guide creates an agent that answers an HTTP request. It walks the dashboard from the New Agent page to a curl call that returns the model’s reply, then shows the same job done from a config file. Use it when you have a running instance and want your first agent, or a new one. The example is a two-stage pipeline named Question answerer. The first stage answers a question sent in a JSON body and the second rewrites the answer as one paragraph.

Before you begin

A running instance with the dashboard open. See Install ServFlow.
An LLM provider. In the sidebar under Configure, open Providers and add one if the list is empty. A sub-agent without a provider cannot run.

Create an agent in the UI

Create the agent

Open the Agents page and click New Agent

In the sidebar under Build, open Agents. Click New Agent in the top right. The New Agent page opens.

The Agents page with the New Agent button in the top right

Choose Start from scratch

Under How to start, choose Start from scratch. The Name and description section appears below it.

The How to start section with three cards: Start from scratch, Use a template, Import a config

Use a template installs a ready-made agent. Import a config takes a config you already have. Both leave you in the same editor as the rest of this guide.

Name the agent and choose an architecture

Enter a Name, for example Question answerer. The Architecture section appears.Choose Sequential pipeline and set Pipeline stages to 2 sub-agents. Each section keeps a summary of your answer on its right edge, so you can change an earlier choice at any point.

The New Agent page with the name filled in and Sequential pipeline selected

Arrangement	What it scaffolds
Sequential pipeline	Sub-agents run in a chain. Each one’s reply feeds the next.
Supervisor / router	A coordinator sub-agent routes work to specialists and collects results.
Parallel fan-out	One entry sub-agent calls several workers, then hands off to an aggregator.

Click Create Agent

Click Create Agent. The editor opens on a canvas with four nodes from top to bottom: the entry, labelled Manual trigger, the sub-agents Analyze request and Compose response, and Final response. The agent is saved, and its id, question-answerer, is derived from the name.

The editor canvas showing the entry, two sub-agent nodes, and the final response

Set the entry

The entry decides how a run starts. A new agent starts as a trigger that runs by hand or on a schedule. To make it answer HTTP requests:

Open the entry panel

Click the Manual trigger node. The Entry panel opens on the right.

Choose the webhook entry type

Under Entry type, choose Webhook — a plain HTTP request starts the agent. A Path field appears.

Enter a path

Enter /ask. The entry node on the canvas relabels to /ask. The agent answers POST requests on that path.

The Entry panel set to Webhook with the path /ask

The other entry types connect the agent to GitHub, Telegram, or Discord, and each has its own fields. See Entry handlers.

Configure the sub-agents

Open the first sub-agent

Click the Analyze request node. Its panel opens.

Choose a provider

Under Provider, choose your provider. The panel confirms with “Calls” and the provider’s name.

Write the prompts

Under Instructions, enter a System prompt:

Answer the question you are given. Be brief and accurate.

Enter a User prompt that reads the request body:

{{ body "question" }}

The body function reads a field from a JSON request body.

The Analyze request panel with a provider chosen and both prompts filled in

Configure the second sub-agent

Click the Compose response node. Choose the same provider and enter a System prompt:

Rewrite the answer you receive as one clear paragraph.

Leave its User prompt empty. In a pipeline, a stage receives the previous stage’s reply.

Save

Click Save in the top bar. The button reads Saved, and the running server picks up the agent without a restart.

Verify

Test the agent from the editor first:

Click Run

Click Run in the top bar. The run dialog asks for a Request body.

Enter a request body and run

Enter the body and click Run:

{ "question": "What is a webhook?" }

The Run dialog with a JSON request body entered

Read the result

The Run panel shows Completed, a log of each sub-agent’s turn, and a Final response block with the reply, the duration, and the conversation thread id. New payload runs it again with a different body.

The Run panel showing a completed run and the final response

Then call it from outside. The response body is the agent’s reply:

curl -X POST http://localhost:8080/ask \
  -H 'Content-Type: application/json' \
  -d '{"question": "What is a webhook?"}'

The body function only reads requests sent with Content-Type: application/json.

Create an agent from the CLI or MCP

If you keep agents in files, describe the agent in a JSON or YAML document and create it with the resource CLI or the management MCP server. Both write to the same store the dashboard uses, and a running server picks up the change without a restart.

CLI

The agent noun of the resource command covers the whole lifecycle. It talks to the SQLite store directly, so it works with no server running.

servflowai resource agent schema                 # JSON Schema for the config document
servflowai resource agent create -f agent.yaml --dry-run
servflowai resource agent create -f agent.yaml
servflowai resource agent list
servflowai resource agent get <config_id>
servflowai resource agent update <config_id> -f agent.yaml
servflowai resource agent enable <config_id>
servflowai resource agent disable <config_id>
servflowai resource agent delete <config_id>

The body is a stored agent: a name, an optional config_id, and the config document under config. A missing config_id is derived from the name.
-f - reads the body from stdin.
--dry-run validates and prints the result without writing.
--set key=value overlays one field by dotted path. Repeat it for more.
--reload is on by default and signals a running server to reload.

The agent from the first section, reduced to one sub-agent, looks like this. Replace providerID with an id from servflowai resource provider list.

name: Question answerer
config:
  entry:
    type: handler
    handlerConfig:
      path: /ask
    start: agent.answer
  agents:
    answer:
      name: Answerer
      providerID: 2
      systemPrompt: Answer the question you are given. Be brief and accurate.
      userPrompt: '{{ body "question" }}'
      next: end

MCP

The management server at /api/mcp exposes the same operations to an AI client. The tools for agents are config_schema, config_example, validate_config, create_config, update_config, list_configs, get_config, delete_config, and set_config_enabled. config_schema and config_example take a kind argument that defaults to agent. A config has to name a real provider and, for a handler entry, a real integration, so list_providers and list_integrations come first. In local and none authentication modes the MCP endpoint is unauthenticated. Anyone who can reach it can administer the instance, so keep it off the public internet. For the shape of the config document, run servflowai resource agent schema and see Agents.

Entry handlers

Every entry type, its fields, and the variables it injects.

Agents

What an agent is made of: entry, sub-agents, and context groups.

Dynamic content

Template functions such as body, param, and secret.

Install ServFlow

Get a running instance if you do not have one yet.

Getting Started

Guides

Running ServFlow

Concepts

References

Before you begin

Create an agent in the UI

Create the agent

Set the entry

Configure the sub-agents

Verify

Create an agent from the CLI or MCP

CLI

MCP

Entry handlers

Agents

Dynamic content

Install ServFlow

​Before you begin

​Create an agent in the UI

​Create the agent

​Set the entry

​Configure the sub-agents

​Verify

​Create an agent from the CLI or MCP

​CLI

​MCP

​Related

Entry handlers

Agents

Dynamic content

Install ServFlow

Before you begin

Create an agent in the UI

Create the agent

Set the entry

Configure the sub-agents

Verify

Create an agent from the CLI or MCP

CLI

MCP

Related