Quick Start

Get running with DataGrout in 5 minutes.

What can you build?

Pick a use case and jump straight to the tools that power it:

Use Case What it does Tools
Cross-system data sync Pull records from one system, reshape them, push to another Discovery, Prism, Flow
Automated reporting Fetch data, aggregate, group, and visualize — on a schedule Frame, Prism (chart), Scheduler
Data exploration Filter, sort, group, pivot, join — no LLM, zero credits Data, Frame
Agent memory Store facts, query knowledge, enforce constraints across sessions Logic
Content security Detect prompt injection before it reaches your agent loops Warden
Scheduled workflows Defer or recur any tool call or multi-step plan Scheduler, Flow
Conditional routing Branch workflows based on data conditions Flow (route)
Numeric computation Generate sequences, compute statistics, detect trends, normalize data, find outliers, rank values Math

All tools work together — chain a Discovery search into a Flow workflow that uses Frame to aggregate and Prism to chart the result.

1. Create a Server

A server is your multiplexed endpoint. All your integrations connect to it, and your agents connect through it.

  1. Click the server dropdown (top-left) and select Create New Server
  2. Enter a name (required) and optional description
  3. Click Create Server

Your server gets a UUID and an MCP endpoint URL:

https://gateway.datagrout.ai/servers/{your-uuid}/mcp

You can find this URL anytime in Settings > Server Info. Copy it – you’ll need it to connect.

2. Create an Access Token

  1. Open the server dropdown and click the Settings icon
  2. Go to the Authentication tab
  3. Click Create Access Token
  4. Give it a name (or leave blank for an auto-generated one)
  5. Copy the token immediately – it won’t be shown again

3. Add an Integration

  1. Go to the Home page (the integrations marketplace)
  2. Find the integration you want (Salesforce, QuickBooks, etc.) and click Add
  3. You’ll be redirected to the integration details page to complete setup

If the integration requires OAuth, you’ll be prompted to authenticate. For MCP servers, provide the server URL and any required credentials.

4. Test It

Option A: Use the Playground

Navigate to the Playground, select your server, and type a goal:

Show me all my customers

The Playground discovers the right tools, builds a plan, and executes it.

Option B: Use the Sandbox

Each integration has a Sandbox tab on its detail page. Select a tool from the dropdown, fill in arguments, and execute it directly in the browser. No agent or SDK required.

Option C: Use the Inspectors

The MCP Inspector and JSONRPC Inspector are free public tools for testing your server connection at the protocol level. Open either inspector, point it at your server URL, and send requests interactively.

Option D: Use cURL (JSONRPC)

The JSONRPC endpoint accepts plain HTTP POST requests with no handshake or session setup:

curl -X POST https://gateway.datagrout.ai/servers/{your-uuid}/rpc \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {your-token}" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/list",
    "params": {}
  }'

The MCP endpoint (/mcp) works with cURL in theory, but requires an SSE initialization handshake and session ID management across requests. The /rpc endpoint is stateless and far simpler for quick testing.

Option E: Use the Conduit SDK

# pip install datagrout-conduit
from datagrout_conduit import Client

client = Client(
    url="https://gateway.datagrout.ai/servers/{your-uuid}/mcp",
    token="{your-token}"
)

tools = client.list_tools()
print(f"{len(tools)} tools available")

# Discover tools by goal
results = client.discover(goal="get customer by email")
for tool in results:
    print(f"  {tool.name} (score: {tool.score:.2f})")

See Conduit SDK for setup in Python, TypeScript, and Rust.

5. Try Discovery

Once connected, use the Discovery tools to find what’s available:

curl -X POST https://gateway.datagrout.ai/servers/{your-uuid}/rpc \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {your-token}" \
  -d '{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/call",
    "params": {
      "name": "data-grout@1/discovery.discover@1",
      "arguments": {
        "goal": "find a customer by email",
        "limit": 5
      }
    }
  }'

Discovery returns ranked tools with semantic scores. Your agent sees only the tools relevant to its goal, not the entire catalog.

Next Steps