Agent NoCode (.NET)

Technology

Built with ASP.NET Core 9.0 & Microsoft Agent Framework

A2A Protocol v0.3.0 Compliant Server

Built with C# and powered by the Microsoft Agent Framework, this agent enables seamless agent-to-agent communication using the standardized A2A protocol. Implemented with ASP.NET Core and the official A2A SDK, it provides dynamic workflow orchestration, multi-agent coordination, and comprehensive health monitoring for distributed agent systems.

Uses Agent Framework Workflows with a graph-based architecture for defining complex agent interactions. Workflows are composed of nodes (representing agents) and edges (representing connections and message flow between agents), enabling sophisticated multi-step reasoning and task delegation patterns.

C# Agent Framework A2A Protocol .NET Documentation

API Endpoints & Documentation

Explore the A2A protocol endpoints, agent cards, and workflow orchestration APIs.

API Documentation Health Status A2A Agent Card

Agent NoCode (.NET) Dashboard

Live monitoring of all subsystems and services. Updates every 30 seconds.

Loading system status...

Quick Start: Chat with Agent

Use this curl command to send a message to the agent via the A2A protocol. The agent will return a task ID that you can use to check the status and results.

Terminal Command

curl -X POST [Loading...]/invoke \
-H "Content-Type: application/json" \
-d '{"input": {"message": "Explain quantum computing in simple terms"}}'

Response:

{
  "task_id": "abc-123...",
  "task_url": "[Loading...]/tasks/abc-123...",
  "status": {"state": "running"}
}

Next Step: Click or curl the task_url to check status and get results.

Configuration Guide

Configure the agent with LLM, database, and authentication settings.

Required Environment Variables

Configure these parameters to enable full agent functionality:

Parameter	Required	Default	Description
Agent Configuration
`AGENT_ID`	Required	`""`	Unique agent identifier (same as DB Agent Id)
`AGENT_NAME`	Optional	`""`	Human-readable agent name
`AGENT_DESCRIPTION`	Optional	`""`	Agent description
LLM Configuration
`LLM_PROVIDER`	Optional	`""`	LLM provider (e.g., azure, openai)
`LLM_ENDPOINT`	Required	`""`	LLM endpoint URL (e.g., https://your-resource.openai.azure.com/)
`LLM_MODEL`	Optional	`""`	LLM model name
`LLM_KEY`	Required	`""`	LLM API key for authentication
`LLM_API_VERSION`	Optional	`""`	LLM API version
`LLM_TEMPERATURE`	Optional	`0.0`	LLM temperature setting
`LLM_MAX_TOKENS`	Optional	`1000`	Maximum tokens for LLM responses
Embeddings Configuration
`EMBED_PROVIDER`	Optional	`""`	Embedding provider (falls back to LLM provider)
`EMBED_MODEL`	Optional	`""`	Embedding model name
`EMBED_API_VERSION`	Optional	`""`	Embedding API version
PostgreSQL (pgvector) Configuration
`PGHOST`	Optional	`""`	PostgreSQL database host
`PGPORT`	Optional	`""`	PostgreSQL database port
`POSTGRES_USER`	Optional	`""`	PostgreSQL database username
`POSTGRES_PASSWORD`	Optional	`""`	PostgreSQL database password
*Authentication Configuration (AUTH_ Environment Variables)**
`AUTH_ENABLED`	Optional	`true`	Enable/disable JWT authentication (default: true)
`AUTH_AUTHORITY`	Required	`""`	OAuth 2.0 authority URL (e.g., https://login.microsoftonline.com/{tenant})
`AUTH_ISSUER`	Optional	`AUTH_AUTHORITY`	Expected issuer claim in JWT tokens (defaults to AUTH_AUTHORITY)
`AUTH_TENANT_ID`	Optional	`""`	Azure AD tenant ID
`AUTH_CLIENT_ID`	Required	`""`	Application client ID (also used as audience)
`AUTH_REDIRECT_URI`	Optional	`""`	OAuth callback/redirect URI
`AUTH_LOGIN_SCOPES`	Optional	`""`	User login scopes (comma-separated, e.g., User.Read,profile)
`AUTH_API_SCOPES`	Optional	`""`	API access scopes (comma-separated)
`AUTH_VALIDATE_ISSUER`	Optional	`true`	Validate token issuer (default: true)
`AUTH_VALIDATE_AUDIENCE`	Optional	`true`	Validate token audience (default: true)
`AUTH_VALIDATE_SIGNING_KEY`	Optional	`true`	Validate token signing key (default: true)
`AUTH_VALIDATE_LIFETIME`	Optional	`true`	Validate token lifetime (default: true)
`AUTH_LIFETIME_SKEW`	Optional	`300`	Clock skew tolerance in seconds (default: 300 = 5 minutes)
A2A Configuration
`AUTOGEN_AGENT_A2A_URL`	Optional	`http://localhost:8001`	Default A2A agent URL
Context & Tools Configuration
`CONTEXTS`	Optional	`[]`	JSON array of context configurations
`TOOL_SERVERS`	Optional	`[]`	JSON array of MCP tool server URLs
Logging Configuration
`LOG_LEVEL`	Optional	`INFO`	Logging level (DEBUG, INFO, WARNING, ERROR)

Example Configuration

.env file

# Agent Configuration
AGENT_ID=my-agent-id
AGENT_NAME=My AI Agent
AGENT_DESCRIPTION=An intelligent AI agent

# LLM Configuration
LLM_PROVIDER=azure
LLM_ENDPOINT=https://your-resource.openai.azure.com/
LLM_MODEL=gpt-4o
LLM_KEY=your-api-key-here
LLM_API_VERSION=2024-02-15-preview
LLM_TEMPERATURE=0.0
LLM_MAX_TOKENS=1000

# Embeddings Configuration (Optional)
EMBED_PROVIDER=azure
EMBED_MODEL=text-embedding-ada-002
EMBED_API_VERSION=2024-02-15-preview

# PostgreSQL Configuration
PGHOST=localhost
PGPORT=5432
POSTGRES_USER=postgres
POSTGRES_PASSWORD=your-password-here

# Authentication Configuration (AUTH_* Environment Variables)
AUTH_ENABLED=true
AUTH_AUTHORITY=https://login.microsoftonline.com/your-tenant-id
AUTH_ISSUER=https://sts.windows.net/your-tenant-id/
AUTH_TENANT_ID=your-tenant-id
AUTH_CLIENT_ID=your-client-id
AUTH_REDIRECT_URI=http://localhost:5017
AUTH_LOGIN_SCOPES=User.Read,profile
AUTH_API_SCOPES=api://your-client-id/.default
AUTH_VALIDATE_ISSUER=true
AUTH_VALIDATE_AUDIENCE=true
AUTH_VALIDATE_SIGNING_KEY=true
AUTH_VALIDATE_LIFETIME=true
AUTH_LIFETIME_SKEW=300

# A2A Configuration
AUTOGEN_AGENT_A2A_URL="http://localhost:8001"

# Context & Tools
CONTEXTS="[]"
TOOL_SERVERS='["http://0.0.0.0:9001/analytics/mcp/"]'

# Logging
LOG_LEVEL=INFO

Sync Parameters to Fabric Developer Workflow Application

Automatically sync your local environment variables to Fabric Developer Workflow Application using the make params command. This eliminates manual configuration in the Application Dashboard.

Prerequisites

Install Fabric Developer Journey CLI from Null Platform:
```
npm install -g @nullplatform/cli
```
Get your API Key:
Go to your App Dashboard from Fabric Workspace → Click user profile icon → Click "Copy personal access token"
Export the API Key:
```
export NP_TOKEN=<your-token>
```
Get your App NRN (Null Resource Name):
1. Go to your Application Dashboard
2. Click the NRN button to copy your application's NRN
3. You'll use this NRN when running the make params command
```
# Format: organization=ID:account=ID:namespace=ID:application=ID
# Example: organization=1234567890:account=9876543210:namespace=1122334455:application=5544332211
```

Run the Command

Once prerequisites are met, run this command in your terminal: