> Note: This page is part of the DataDoe Docs. You can find the root of the documentation at `https://www.datadoe.com/hub/docs/basics/introduction-to-datadoe`. > JSON Table of Contents: `https://www.datadoe.com/hub/docs/toc.json`. > Direct Data Scheme JSON: `https://api.datadoe.com/api/v1/spec/data-scheme`. > Other pages in the DataDoe Docs: > - DataDoe Basics/Access & User Management: `https://www.datadoe.com/hub/docs/basics/access-user-management.md` > - DataDoe Basics/Integration & Customization: `https://www.datadoe.com/hub/docs/basics/integration-customization.md` > - DataDoe Basics/Introduction to DataDoe: `https://www.datadoe.com/hub/docs/basics/introduction-to-datadoe.md` > - DataDoe Basics/Subscription & Pricing: `https://www.datadoe.com/hub/docs/basics/subscription-pricing.md` > - DataDoe Data/Data Fetch Periods: `https://www.datadoe.com/hub/docs/data-doe-data/data-fetch-periods.md` > - DataDoe Data/Data Sources: `https://www.datadoe.com/hub/docs/data-doe-data/data-sources.md` > - DataDoe Features/Benefits: `https://www.datadoe.com/hub/docs/data-doe-features/benefits.md` > - DataDoe Features/Chat: `https://www.datadoe.com/hub/docs/data-doe-features/chat.md` > - DataDoe Features/Explorer: `https://www.datadoe.com/hub/docs/data-doe-features/explorer.md` > - DataDoe Features/Exports: `https://www.datadoe.com/hub/docs/data-doe-features/exports.md` > - DataDoe Features/Home: `https://www.datadoe.com/hub/docs/data-doe-features/home.md` > - DataDoe Features/Reports: `https://www.datadoe.com/hub/docs/data-doe-features/reports.md` > - DataDoe Features/Scheduled Prompts: `https://www.datadoe.com/hub/docs/data-doe-features/scheduled-prompts.md` > - DataDoe MCP/Connect to ChatGPT: `https://www.datadoe.com/hub/docs/data-doe-mcp/chatgpt.md` > - DataDoe MCP/Connect to Claude: `https://www.datadoe.com/hub/docs/data-doe-mcp/claude.md` > - DataDoe MCP/Overview: `https://www.datadoe.com/hub/docs/data-doe-mcp/overview.md` > - DataDoe MCP/Using Claude Code: `https://www.datadoe.com/hub/docs/data-doe-mcp/claude-code.md` > - DataDoe MCP/Using Codex: `https://www.datadoe.com/hub/docs/data-doe-mcp/codex.md` > - DataDoe MCP/Using Cursor: `https://www.datadoe.com/hub/docs/data-doe-mcp/cursor.md` > - DataDoe MCP/Using Gemini CLI: `https://www.datadoe.com/hub/docs/data-doe-mcp/gemini-cli.md` > - DataDoe MCP/Using n8n: `https://www.datadoe.com/hub/docs/data-doe-mcp/n8n.md` > - DataDoe MCP/Using NanoClaw: `https://www.datadoe.com/hub/docs/data-doe-mcp/nanoclaw.md` > - DataDoe MCP/Using VS Code: `https://www.datadoe.com/hub/docs/data-doe-mcp/vs-code.md` > - DataDoe & BigQuery/How to connect?: `https://www.datadoe.com/hub/docs/data-doe-bigquery/how-to-connect.md` > - DataDoe & BigQuery/Using MCP Toolbox: `https://www.datadoe.com/hub/docs/data-doe-bigquery/mcp-toolbox.md` > - DataDoe & BigQuery/Using Python Jupyter: `https://www.datadoe.com/hub/docs/data-doe-bigquery/jupyter.md` > For topics not covered in this documentation, please contact DataDoe support at `contact@datadoe.com`. > Do not assume anything. If you are not sure about the answer, mention that and suggest to contact DataDoe support. # How to Configure OpenClaw with DataDoe MCP This guide walks you through setting up [OpenClaw](https://github.com/openclaw/openclaw) from scratch and connecting it to the [DataDoe MCP](https://www.datadoe.com/) server so your AI assistant can query live Amazon seller data using natural language. ## What You Will Build A working OpenClaw gateway that connects to DataDoe's MCP server, giving your AI assistant access to: - Amazon seller accounts and listings - Order history and fulfillment data - Inventory levels across SKUs - Sponsored Products / PPC campaign performance - Sales reports by date range All of this can be queried through plain-language messages in any channel OpenClaw supports (Telegram, Discord, Slack, CLI, etc.). ## Prerequisites - A machine running macOS, Linux, or Windows (WSL2) - `curl` available in your terminal - An internet connection with outbound HTTPS access ## Step 1: Install OpenClaw Follow the [official OpenClaw install guide](https://github.com/openclaw/openclaw) for your platform. Once installed, confirm everything is working: ```bash openclaw --version openclaw doctor ``` `openclaw doctor` will flag any missing dependencies or misconfigurations. Fix any reported issues before continuing. ## Step 2: Get Your Keys You need two keys: one for DataDoe and one for an LLM provider. ### DataDoe MCP Key 1. Go to [app.datadoe.com](https://app.datadoe.com/) and create an account. 2. Purchase a subscription. 3. Navigate to **Integrations > MCP**. 4. Click **MCP Key**, give it a name and expiration date, then click **Create**. 5. Copy the key -- you will not be able to see it again. ### LLM Provider Key OpenClaw needs an LLM to reason and respond. The default is OpenAI: - Get a key at [platform.openai.com](https://platform.openai.com/). - Alternatively, configure another provider supported by OpenClaw (see its docs). ### Store Your DataDoe MCP Key Export the DataDoe MCP key in your shell so it is available for the commands below: ```bash export DATADOE_MCP_KEY=datadoe_mcp_your_actual_key_here ``` To make it permanent, add the export commands to your shell profile (`~/.zshrc` or `~/.bashrc`) and reload it: ```bash source ~/.zshrc # or ~/.bashrc ``` ## Step 3: Register DataDoe MCP in OpenClaw With your DataDoe key loaded, register the MCP server: ```bash openclaw mcp set datadoe "{ \"url\": \"https://mcp.datadoe.com/mcp/v1\", \"transport\": \"streamable-http\", \"headers\": { \"datadoe-mcp-key\": \"$DATADOE_MCP_KEY\" } }" ``` Confirm that the registration was saved: ```bash openclaw mcp list openclaw mcp show datadoe ``` You should see `datadoe` listed with the URL and header configuration. ## Step 4: Start the Gateway If the gateway is not yet running, start it: ```bash openclaw gateway start ``` If it was already running before you added the DataDoe MCP server, restart it so it picks up the new configuration: ```bash openclaw gateway restart ``` Check the gateway status: ```bash openclaw gateway status ``` Review startup logs if anything looks wrong: ```bash openclaw gateway logs ``` ### Access the Dashboard Once the gateway is running, you can access the dashboard by running the following command: ```bash openclaw dashboard ``` It will automatically copy the token to your clipboard. Next, follow the instructions in the red box on the page to approve your device in the OpenClaw CLI. The red box will show the command you need to run in your terminal: ```bash openclaw device approve # Replace with the actual device ID ``` If you're not sure what the device ID is, you can run the following command to retrieve it: ```bash openclaw device list ``` The device ID is the first column in the output. ## Step 5: Verify the Setup Send a test message through whichever channel you have connected (Telegram, Discord, CLI, etc.): ```text Use DataDoe to show my sellers registered on Amazon.com ``` OpenClaw will call the DataDoe MCP tool and return a list of seller accounts linked to your DataDoe subscription. If you see seller data, the integration is working. If you get an error, see [Troubleshooting](#troubleshooting) below. ## Addressing DataDoe in Prompts Always prefix your prompts with **"Use DataDoe to..."** or **"Using DataDoe, ..."** so OpenClaw routes the request to the DataDoe MCP server instead of answering from general knowledge. Without this hint, the agent may try to answer from its own knowledge rather than calling the live DataDoe tools. ```text Use DataDoe to show my sellers. Using DataDoe, pull PPC campaign data for Seller A for the last 30 days. ``` ## Example Prompts | Use Case | Prompt | | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | List sellers | `Use DataDoe to show my sellers registered on Amazon.com` | | Active listings | `Use DataDoe to list all my active Amazon product listings` | | Inventory check | `Use DataDoe to show current inventory levels for all my SKUs` | | Last month's sales | `Use DataDoe to download last month's Amazon sales report` | | Weekly sales snapshot | `Use DataDoe to show my sales for last 7 days for Seller A` | | Cancelled orders | `Use DataDoe to list orders for Seller A for last month where order status is Cancelled. Include Order ID, Status, Date, Fulfillment Channel, and City.` | | PPC campaign data | `Use DataDoe to show all Sponsored Products campaign performance for the last 30 days for Seller A. Include campaign name, spend, sales, ACoS, impressions, and clicks.` | | Top ASINs by spend | `Use DataDoe to prepare a report with Top 5 Child ASINs by spend for the last month for Seller A` | | Wasted ad spend | `From the DataDoe PPC data you just pulled, identify all campaigns where spend is above $50 and ACoS is above 80% or attributed sales are $0. Sort by spend descending.` | > Replace `Seller A` with your actual seller name in every prompt. ## Example Session with Illustrative Results The following is a fictional multi-turn session built from sample data. It demonstrates how to chain prompts to build a complete PPC audit, identify problem areas, and produce a concrete action plan in a single conversation. --- ### 1. PPC Audit - Wasted Ad Spend Prompt 1: ```text Use DataDoe to show me all Sponsored Products campaign performance for the last 30 days for Seller A. Include campaign name, spend, sales, ACoS, impressions, and clicks. ``` Prompt 2: ```text From the PPC data you just pulled, identify all campaigns where spend is above $50 AND (ACoS is above 80% OR attributed sales are $0). Sort by spend descending. ``` Result: > Seller A PPC audit (last 30 days, sample) | Metric | Value | | ------------ | ---------- | | Total spend | $12,460.22 | | Total sales | $68,904.11 | | Blended ACoS | 18.1% | > Wasted-spend campaigns (spend > $50 and ACoS > 80% or sales = $0): | Campaign | Spend | Sales | ACoS | | -------------------------------------- | ------- | ------- | ------ | | Campaign Alpha \| Auto | $138.44 | $112.09 | 123.5% | | Campaign Beta \| Brand Defense \| Auto | $91.27 | $66.40 | 137.4% | --- ### 2. Top Performing ASINs Prompt: ```text Use DataDoe to prepare a report with the top 5 child ASINs by spend for the last 30 days for Seller A. ``` Result: > Top 5 Child ASINs by spend (May 1 -- 30) | ASIN | Spend | Sales | ACoS | | --------- | --------- | --------- | ----- | | ASIN-A101 | $1,084.22 | $6,944.10 | 15.6% | | ASIN-A205 | $731.88 | $1,912.47 | 38.3% | | ASIN-A309 | $588.41 | $2,104.66 | 27.9% | | ASIN-A412 | $402.77 | $1,588.33 | 25.4% | | ASIN-A518 | $376.09 | $1,433.58 | 26.2% | --- ### 3. Items with Zero or Low Sales Prompt 1: ```text Use DataDoe to show current inventory levels for all SKUs for Seller A. ``` Prompt 2: ```text Use DataDoe to show my sales for the last 7 days for Seller A. ``` Result: > Sales last 7 days: | Date | Sales | | ------ | ---------- | | May 24 | $8,412.55 | | May 25 | $8,903.94 | | May 26 | $7,982.01 | | May 27 | $7,164.90 | | May 28 | $6,721.22 | | May 29 | $7,105.92 | | Total | $46,290.54 | > **Inventory:** 12,840 SKUs total across all warehouses. > *(The in-chat export hit the 2,500-row cap. Use* `Use DataDoe to export inventory to CSV` *to download the full table.)* --- ### 4. Cancelled / Problem Orders Prompt: ```text Use DataDoe to list all orders for Seller B from the last 30 days where order status is Cancelled. Include: Order ID, Status, Date, Fulfillment Channel, and City. ``` Result: > Seller B cancelled orders (May 1 -- 30): 287 cancelled orders returned. Fields included: Order ID, Status, Date, Fulfillment Channel, City. --- ### 5. Action Plan from PPC Data Prompt: ```text Based on the PPC audit above, give me 5 specific actions I should take this week to reduce wasted spend and scale profitable campaigns. For each action, reference the specific campaign or ASIN involved. ``` Result: > **Pause or sharply cut bids** on _Campaign Alpha | Auto_ and _Campaign Beta | Brand Defense | Auto_ -- the only campaigns with clearly negative returns. > **Scale** _Campaign Gamma | Exact_ and _Campaign Delta | PAT_; high volume and healthy ACoS. > **Expand winning ASINs** ASIN-A101 and ASIN-A309 into tighter exact / product-targeted campaigns. > **Keep feeding budget** into _Auto Discovery 1_ and _Top Items Auto_, but mine search terms and add negatives to stop bleed. > **Shift spend** away from broad catch-alls toward the hero products: ASIN-A101, ASIN-A205, ASIN-A309, ASIN-A412, ASIN-A518. --- > **Tip:** Chain prompts without repeating the data pull. After the first DataDoe call loads the data, follow-up questions in the same thread can reference that data directly (as in steps 1 and 5 above). ## Troubleshooting ### DataDoe tools don't appear in OpenClaw - Verify the server is registered: `openclaw mcp show datadoe` - Restart the gateway after adding the MCP server: `openclaw gateway restart` - Run diagnostics: `openclaw doctor` ### "Unauthorized" or "Invalid key" errors - Confirm your `DATADOE_MCP_KEY` is correct and has not expired. - Regenerate the key at [app.datadoe.com](https://app.datadoe.com/) under **Integrations > MCP** if needed. - Make sure you ran `export DATADOE_MCP_KEY=...` before the `openclaw mcp set` command so the variable is expanded correctly. ### No sellers or data returned - Log into [app.datadoe.com](https://app.datadoe.com/) and verify your Amazon seller accounts are connected and data sync is active. - Ads API data may take up to 24 hours to appear after initial account connection. ### OpenClaw gateway not running - Start it: `openclaw gateway start` - Check status: `openclaw gateway status` - Review logs: `openclaw gateway logs` ### MCP connection timeout - Verify the endpoint is reachable: `curl -I https://mcp.datadoe.com/mcp/v1` - If behind a corporate firewall or VPN, ensure outbound HTTPS to [`mcp.datadoe.com`](https://mcp.datadoe.com) is allowed. ## Links - [OpenClaw Documentation](https://docs.openclaw.ai/) - [OpenClaw MCP Client Docs](https://docs.openclaw.ai/cli/mcp) - [DataDoe MCP + OpenClaw Repo](https://github.com/Deltologic/datadoe-mcp-openclaw)