Load Respond.io data to DuckDB

respond.io is a customer messaging platform that provides a REST API for automating messages, managing contacts, and triggering workflows. Everything needed to build a working Respond.io → DuckDB pipeline is on this page: the API's base URL, authentication, endpoints, pagination and incremental field — plus a prompt that hands the whole job to your coding agent.

---

Build your Respond.io to DuckDB pipeline

Paste this prompt into Claude, Codex, or Cursor. The agent does the rest.

PromptCopy prompt
Run uvx dlthub-init@latest to build a pipeline from Respond.io to DuckDB and run it on dltHub

That scaffolds a dltHub workspace and installs the dltHub AI harness — the project rules, the secrets-management skill, and the dlt MCP server your agent needs to work safely. From there it reads the Respond.io API, proposes the endpoints to load, then writes, runs and validates the pipeline while you review rather than type. Credentials are inspected through MCP tools, so your agent never reads secrets.toml itself. How the LLM-native workflow works →

Prefer to write it yourself? Every fact the agent uses is below.

---

Respond.io API at a glance

These values come from the Respond.io API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Respond.io API?

Authentication is performed by including an API Access Token in the Authorization header using the Bearer scheme. Tokens are generated within the respond.io workspace settings.

1. Get your credentials

To obtain your respond.io API credentials, ensure your workspace is on the Growth Plan or higher. Log in to your respond.io account and navigate to Settings > Integrations > Developer API. Click on Add Access Token to generate a new token, then copy and store it securely, as it will be required for API authentication.

2. Add them to .dlt/secrets.toml

Copy
[sources.respond_io_source]
api_token = "your_api_token_here"

dlt reads this file automatically at runtime. With the harness, the setup-secrets skill prompts you for the values and never handles the raw credential in chat. For production, see setting up credentials with dlt.

---

What Respond.io data can I load into DuckDB?

These are the Respond.io endpoints dlt can load into DuckDB:

---

How do I load only new Respond.io records?

Respond.io exposes cursorId on v2/contacts, so dlt can request only the records that changed since the last run. Set it as the cursor_path and dlt tracks the high-water mark for you between runs.

Copy
{"name": "contacts", "endpoint": {
    "path": "v2/contacts",
    "data_selector": "items",
    "incremental": {"cursor_path": "cursorId", "initial_value": "2024-01-01T00:00:00Z"},
}}

On the first run dlt loads everything from initial_value; on every run after that it requests only what changed and appends with write_disposition="merge" if you set a primary key. See incremental loading.

---

What does the generated Respond.io pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading contacts and conversations from the Respond.io API into DuckDB:

Copy
import dlt
from dlt.sources.rest_api import RESTAPIConfig, rest_api_resources

@dlt.source
def respond_io_source(api_token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.respond.io/v2",
            "auth": {"type": "bearer", "token": api_token},
        },
        "resources": [
            {"name": "contacts", "endpoint": {"path": "v2/contacts", "data_selector": "items"}},
            {"name": "messages", "endpoint": {"path": "v2/messages", "data_selector": "items"}}
        ],
    }
    yield from rest_api_resources(config)


def load_respond_io_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="respond_io_pipeline",
        destination="duckdb",
        dataset_name="respond_io_data",
    )
    load_info = pipeline.run(respond_io_source())
    print(load_info)


if __name__ == "__main__":
    load_respond_io_to_duckdb()

Run it with python respond_io_pipeline.py. The agent iterates on this until it loads cleanly — you review and approve, rather than write it from scratch.

---

How do I query Respond.io data in DuckDB?

dlt creates one table per resource. Query the loaded data with Python or SQL — or ask your agent to, through the MCP server's execute_sql_query tool.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("respond_io_pipeline").dataset()
df = data.contacts.df()
print(df.head())

SQL:

Copy
SELECT * FROM respond_io_data.contacts LIMIT 10;

See querying your data with dataset and exploring it in marimo notebooks.

---

How do I deploy the Respond.io to DuckDB pipeline in production?

The pipeline runs locally, which is ideal for prototyping and one-off analysis. When you need it on a schedule, monitored on every load, and shared with your team, deploy the same dlt code on the dltHub platform — no infrastructure to maintain. The prompt above already ends with "run it on dltHub", so your agent can take it there directly.

• Deploy & schedule — run the pipeline as a managed job with automatic retries.
• Monitor — observable job queues, alerting, and load metrics for every run.
• Transform — promote raw Respond.io loads into governed, documented models.
• Visualize & share — explore data in notebooks and publish live dashboards instead of static screenshots.

Book a demo →

---

What other destinations can I load Respond.io data to?

dlt loads into any of these — only the destination argument changes:

Set dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. On the dltHub platform the same pipeline runs against a managed Iceberg lakehouse. See the full destinations list.

---

Next steps

• Ready for production? Book a demo of the dltHub platform →
• dlt LLM-native workflow docs
• REST API source reference
• Join the dlt community on Slack