Skip to main content
DataDoe HubHub
(opens in a new tab)
ChatGPT (opens in a new tab)
Claude (opens in a new tab)

Using OpenCode with DataDoe MCP

OpenCode (opens in a new tab) is an open-source AI coding agent built for the terminal. It supports a TUI, CLI, and desktop app, and works with major LLM providers such as Anthropic, OpenAI, and Google. Unlike browser-based assistants, OpenCode runs in your terminal alongside your code, making it a natural fit for scaffolding projects, writing scripts, and building tools that use live data.

In this setup, DataDoe MCP acts as the data layer for OpenCode. Your agent calls DataDoe tools to read live Amazon Seller, Vendor, and Ads data on demand, without manual exports or custom SP-API pipelines.

What you will build

By the end of this tutorial, you will have:

  • OpenCode installed and running on your machine
  • An LLM provider configured (Anthropic, OpenAI, or OpenCode Zen)
  • DataDoe MCP connected via the ~/.config/opencode/opencode.jsonc config file
  • A verified first query listing your connected Amazon sellers
  • A seven-day sales report generated directly in the terminal
  • A self-contained dashboard.html sales dashboard built by OpenCode using live DataDoe data, ready to open in any browser

Prerequisites

Step 1: Install OpenCode

Install OpenCode using the method that suits your platform:

bash
1# One-liner (recommended)
2curl -fsSL https://opencode.ai/install | bash
3
4# Node.js (npm, bun, pnpm, or yarn)
5npm i -g opencode-ai@latest
6
7# macOS and Linux (Homebrew — always up to date)
8brew install anomalyco/tap/opencode
9
10# Windows
11scoop install opencode
12choco install opencode

A desktop app is also available if you prefer a graphical interface. Download it from opencode.ai/download (opens in a new tab) for macOS, Windows, or Linux.

Verify the installation:

bash
1opencode --version

Step 2: Configure an LLM provider and choose a model

Navigate to any directory and run opencode to open the TUI. You have two options for connecting an LLM:

Option A — OpenCode Zen (no external API key required)

Run /connect inside the TUI, select opencode, and sign in at opencode.ai/auth (opens in a new tab). Zen provides a curated set of models maintained by the OpenCode team, so you do not need an Anthropic or OpenAI account.

Option B — your own API key

Run /model inside the TUI to open the model picker:

  1. Select a provider — OpenCode supports Anthropic, OpenAI, Google, Mistral, and more
  2. Choose an authentication method: API key
  3. Paste your key
  4. Select a model, for example claude-sonnet-4-6

Build vs. plan mode. OpenCode has two built-in agent modes: build (default, full file access) and plan (read-only, for analysis and exploration). Switch between them with the Tab key. For this tutorial, stay in build mode.

Step 3: Connect DataDoe MCP

Important: OpenCode does not currently support adding remote authenticated MCP servers with a CLI command. You must configure DataDoe MCP by editing the config file manually in a text editor such as VS Code, nano, or vim.

Open ~/.config/opencode/opencode.jsonc in your preferred text editor and add the following block:

jsonc
1{
2    "$schema": "https://opencode.ai/config.json",
3    "mcp": {
4        "datadoe-mcp": {
5            "type": "remote",
6            "url": "https://mcp.datadoe.com/mcp/v1",
7            "enabled": true,
8            "headers": {
9                "datadoe-mcp-key": "YOUR_DATADOE_MCP_KEY"
10            }
11        }
12    }
13}

Replace YOUR_DATADOE_MCP_KEY with your key from DataDoe MCP Integrations (opens in a new tab).

Save the file. Before restarting OpenCode, you can verify that the config is picked up correctly by running the following command in your terminal:

bash
1opencode mcp list

This lists all configured MCP servers and their status. You should see datadoe-mcp with a connected or enabled state.

If datadoe-mcp does not appear, check that the config file is saved at ~/.config/opencode/opencode.jsonc and that it contains valid JSON with no trailing commas and correct indentation.

Now restart OpenCode (press cmd + c to quit, then run opencode again) to load the MCP server into the active session.

Quick setup reference

If you are already familiar with OpenCode MCP configuration, here is everything you need:

Config:   ~/.config/opencode/opencode.jsonc  →  mcp.datadoe-mcp
URL:      https://mcp.datadoe.com/mcp/v1
Header:   datadoe-mcp-key: YOUR_DATADOE_MCP_KEY

Step 4: Verify the MCP connection

Restart OpenCode and open a new session, then ask:

What DataDoe tools do you have access to?

OpenCode should respond with a list of DataDoe MCP tools, such as list_sellers, query_table, and others. If no tools appear, check that the config file contains valid JSON with correct indentation and that the MCP key is correct.

Step 5: First conversation and seven-day sales report

List your connected sellers

Start with a simple query to confirm that DataDoe data flows through the connection:

List my all available sellers on Amazon

OpenCode calls list_sellers through DataDoe MCP and returns the names of your connected accounts. Note the seller name, as you will use it in the next query.

Generate a seven-day sales report

Now use OpenCode to produce a business report. Paste the prompt below, replacing {example_seller} with your seller name:

Prepare me a sales summary for {example_seller} seller for last 7 days

OpenCode will:

  1. Call list_sellers to confirm the account
  2. Query the Profit by SKU & Date table for the last seven days
  3. Analyse the data and return a structured markdown report with per-SKU breakdowns, daily rows, and executive KPIs (total sales, units sold, profit, ACoS, TACoS, ROI)

Step 6: Build a sales dashboard HTML page

This step shows OpenCode's full coding agent capability: it fetches live Amazon data from DataDoe and writes a complete, self-contained HTML dashboard into your project folder. No server or build step is required.

Setup

Create a new project directory and open OpenCode inside it:

bash
1mkdir sales-dashboard && cd sales-dashboard
2opencode

Prompt

Paste the following prompt, replacing {example_seller} with your seller name:

Using DataDoe MCP, fetch the 7-day sales data for my {example_seller} seller and create
a self-contained HTML file called dashboard.html with a sales dashboard. Include:
- KPI cards at the top: total revenue, total units sold, total profit, average ACoS
- A daily revenue chart (bar chart) using Chart.js from CDN
- A table of top 5 products by profit with columns: SKU, ASIN, total revenue, units sold, profit, ROI
Use clean modern inline CSS, no external stylesheets. All data must come from DataDoe tools.

What OpenCode does

  1. Calls list_sellers and query_table on Profit by SKU & Date to fetch the seven-day data
  2. Aggregates daily revenue and per-SKU totals
  3. Scaffolds dashboard.html with Chart.js (loaded from CDN), KPI summary cards, a daily bar chart, and a top-5 product table
  4. Writes the file to the current directory
html
1<!DOCTYPE html>
2<html lang="en">
3    <head>
4        <meta charset="UTF-8" />
5        <meta name="viewport" content="width=device-width, initial-scale=1.0" />
6        <title>Delto UK - 7-Day Sales Dashboard</title>
7        <script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.7/dist/chart.umd.min.js"></script>
8        <style>
9            * {
10                margin: 0;
11                padding: 0;
12                box-sizing: border-box;
13                font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
14            }
15            body {
16                background: #f0f2f5;
17                padding: 30px;
18                color: #1a1a2e;
19            }
20            .dashboard {
21                max-width: 1200px;
22                margin: 0 auto;
23            }
24            h1 {
25                font-size: 26px;
26                margin-bottom: 6px;
27            }
28            .subtitle {
29                color: #666;
30                font-size: 14px;
31                margin-bottom: 24px;
32            }
33            .kpi-grid {
34                display: grid;
35                grid-template-columns: repeat(4, 1fr);
36                gap: 16px;
37                margin-bottom: 24px;
38            }
39            .kpi-card {
40                background: #fff;
41                border-radius: 12px;
42                padding: 20px;
43                box-shadow: 0 1px 4px rgba(0, 0, 0, 0.08);
44            }
45            .kpi-label {
46                font-size: 12px;
47                text-transform: uppercase;
48                letter-spacing: 0.5px;
49                color: #888;
50                margin-bottom: 6px;
51            }
52            .kpi-value {
53                font-size: 28px;
54                font-weight: 700;
55            }
56            .kpi-value.green {
57                color: #16a34a;
58            }
59            .kpi-value.blue {
60                color: #2563eb;
61            }
62            .kpi-value.purple {
63                color: #7c3aed;
64            }
65            .kpi-value.orange {
66                color: #ea580c;
67            }
68            .chart-section {
69                background: #fff;
70                border-radius: 12px;
71                padding: 24px;
72                box-shadow: 0 1px 4px rgba(0, 0, 0, 0.08);
73                margin-bottom: 24px;
74            }
75            .chart-section h2 {
76                font-size: 16px;
77                margin-bottom: 16px;
78            }
79            .chart-wrap {
80                position: relative;
81                height: 320px;
82            }
83            .table-section {
84                background: #fff;
85                border-radius: 12px;
86                padding: 24px;
87                box-shadow: 0 1px 4px rgba(0, 0, 0, 0.08);
88            }
89            .table-section h2 {
90                font-size: 16px;
91                margin-bottom: 16px;
92            }
93            table {
94                width: 100%;
95                border-collapse: collapse;
96            }
97            th {
98                text-align: left;
99                padding: 10px 12px;
100                font-size: 12px;
101                text-transform: uppercase;
102                letter-spacing: 0.4px;
103                color: #888;
104                border-bottom: 2px solid #e5e7eb;
105            }
106            td {
107                padding: 10px 12px;
108                font-size: 14px;
109                border-bottom: 1px solid #f0f0f0;
110            }
111            tr:last-child td {
112                border-bottom: none;
113            }
114            tr:hover td {
115                background: #f9fafb;
116            }
117            .text-right {
118                text-align: right;
119            }
120            .text-green {
121                color: #16a34a;
122            }
123        </style>
124    </head>
125    <body>
126        <div class="dashboard">
127            <h1>Delto UK — 7-Day Sales Dashboard</h1>
128            <p class="subtitle">10 Jun – 17 Jun 2026 &middot; Data via DataDoe</p>
129
130            <div id="kpis" class="kpi-grid"></div>
131
132            <div class="chart-section">
133                <h2>Daily Revenue (GBP)</h2>
134                <div class="chart-wrap"><canvas id="revenueChart"></canvas></div>
135            </div>
136
137            <div class="table-section">
138                <h2>Top 5 Products by Profit</h2>
139                <table>
140                    <thead>
141                        <tr>
142                            <th>SKU</th>
143                            <th>ASIN</th>
144                            <th class="text-right">Total Revenue</th>
145                            <th class="text-right">Units Sold</th>
146                            <th class="text-right">Profit</th>
147                            <th class="text-right">ROI</th>
148                        </tr>
149                    </thead>
150                    <tbody id="topProducts"></tbody>
151                </table>
152            </div>
153        </div>
154
155        <script>
156            const dailyData = [
157                { date: '2026-06-10', sales: 9206.11, units: 1281, profit: 5612.52, acos: 21.21 },
158                { date: '2026-06-11', sales: 8956.88, units: 1217, profit: 5451.63, acos: 23.17 },
159                { date: '2026-06-12', sales: 8512.72, units: 1124, profit: 5053.9, acos: 23.34 },
160                { date: '2026-06-13', sales: 8432.64, units: 1114, profit: 5037.35, acos: 22.25 },
161                { date: '2026-06-14', sales: 8272.24, units: 1102, profit: 5062.28, acos: 22.86 },
162                { date: '2026-06-15', sales: 3951.41, units: 543, profit: 1914.89, acos: 23.27 },
163                { date: '2026-06-16', sales: 0, units: 0, profit: -739.6, acos: 24.9 },
164                { date: '2026-06-17', sales: 0, units: 0, profit: -21.13, acos: 50.79 }
165            ];
166
167            const topProducts = [
168                {
169                    sku: '286_5214_UK_bkqnk_ctf_FBA',
170                    asin: 'B0UIBG392T',
171                    sales: 3586.4,
172                    units: 359,
173                    profit: 2000.68,
174                    roi: 63.29
175                },
176                {
177                    sku: '43_1_3017_m_ball_FBA',
178                    asin: 'B033B4S05B',
179                    sales: 1182.21,
180                    units: 91,
181                    profit: 675.07,
182                    roi: 93.52
183                },
184                {
185                    sku: 'SET_9_TQVRWGQB_ctf_FBA',
186                    asin: 'B0B2JO7LH3',
187                    sales: 909.16,
188                    units: 140,
189                    profit: 462.53,
190                    roi: 59.43
191                },
192                {
193                    sku: '30_9749_aluminum_block_FBA_SnL',
194                    asin: 'B0HX5GGN1M',
195                    sales: 608.16,
196                    units: 122,
197                    profit: 442.03,
198                    roi: 209.66
199                },
200                {
201                    sku: '249_7421_UK_shpmo_ctf_FBA',
202                    asin: 'B0CGQVMC6U',
203                    sales: 515.73,
204                    units: 61,
205                    profit: 374.29,
206                    roi: 182.29
207                }
208            ];
209
210            const totalRevenue = dailyData.reduce((s, d) => s + d.sales, 0);
211            const totalUnits = dailyData.reduce((s, d) => s + d.units, 0);
212            const totalProfit = dailyData.reduce((s, d) => s + d.profit, 0);
213            const avgAcos = dailyData.reduce((s, d) => s + d.acos, 0) / dailyData.length;
214
215            const fmt = (n, d = 2) => '£' + n.toFixed(d).replace(/\B(?=(\d{3})+(?!\d))/g, ',');
216            const fmtUnits = n => n.toLocaleString();
217
218            document.getElementById('kpis').innerHTML = `
219  <div class="kpi-card"><div class="kpi-label">Total Revenue</div><div class="kpi-value blue">${fmt(totalRevenue, 2)}</div></div>
220  <div class="kpi-card"><div class="kpi-label">Total Units Sold</div><div class="kpi-value purple">${fmtUnits(totalUnits)}</div></div>
221  <div class="kpi-card"><div class="kpi-label">Total Profit</div><div class="kpi-value green">${fmt(totalProfit, 2)}</div></div>
222  <div class="kpi-card"><div class="kpi-label">Average ACoS</div><div class="kpi-value orange">${avgAcos.toFixed(2)}%</div></div>
223`;
224
225            const labels = dailyData.map(d => {
226                const p = d.date.split('-');
227                return p[2] + '/' + p[1];
228            });
229            const values = dailyData.map(d => d.sales);
230
231            new Chart(document.getElementById('revenueChart'), {
232                type: 'bar',
233                data: {
234                    labels,
235                    datasets: [
236                        {
237                            label: 'Revenue (GBP)',
238                            data: values,
239                            backgroundColor: values.map(v =>
240                                v > 0 ? 'rgba(37,99,235,.75)' : 'rgba(200,200,200,.4)'
241                            ),
242                            borderColor: values.map(v => (v > 0 ? '#2563eb' : '#ccc')),
243                            borderWidth: 1,
244                            borderRadius: 4
245                        }
246                    ]
247                },
248                options: {
249                    responsive: true,
250                    maintainAspectRatio: false,
251                    plugins: {
252                        legend: { display: false }
253                    },
254                    scales: {
255                        y: {
256                            beginAtZero: true,
257                            ticks: { callback: v => '£' + v.toLocaleString() },
258                            grid: { color: 'rgba(0,0,0,.06)' }
259                        },
260                        x: {
261                            grid: { display: false }
262                        }
263                    }
264                }
265            });
266
267            document.getElementById('topProducts').innerHTML = topProducts
268                .map(
269                    p => `
270  <tr>
271    <td style="font-family:monospace;font-size:13px">${p.sku}</td>
272    <td style="font-family:monospace;font-size:13px">${p.asin}</td>
273    <td class="text-right">${fmt(p.sales, 2)}</td>
274    <td class="text-right">${fmtUnits(p.units)}</td>
275    <td class="text-right text-green">${fmt(p.profit, 2)}</td>
276    <td class="text-right">${p.roi.toFixed(1)}%</td>
277  </tr>
278`
279                )
280                .join('');
281        </script>
282    </body>
283</html>

Verify the result

Open the generated file in your browser:

bash
1# macOS
2open dashboard.html
3
4# Windows
5start dashboard.html
6
7# Linux
8xdg-open dashboard.html

The page is fully self-contained, so no web server or additional dependencies are required.

Note: The dashboard is generated from live data at the time of running. Re-run the same prompt at any time to refresh the data.

Related resources

DataDoe MCP resources

Check the following resources for more information: