pangolinfo-mcp

# pangolinfo-mcp

> Pangolinfo MCP server — **18 Amazon e-commerce & IP data tools** for AI assistants via [Model Context Protocol](https://modelcontextprotocol.io).

**🔗 Official site: [www.pangolinfo.com](https://www.pangolinfo.com/?sourceTag=mcp_)**

Plug your favorite AI client (Claude Code, Cursor, Cline, Windsurf, Codex, Hermes, OpenClaw) into Pangolinfo's Amazon scrape APIs and let the AI run keyword research, listing analysis, review mining, niche discovery, category navigation, AI search lookups, keyword-trend checks, and WIPO trademark clearance — all from natural-language instructions.

> ⚠️ **BREAKING CHANGE in 0.7.0 — `pacer_search` retired, merged into `wipo_search`**
>
> The standalone `pacer_search` tool was removed. US patent-litigation (PACER) lookups
> are now reached by passing `enableLitigation=true` to `wipo_search` — it finds the patent
> and joins the related US litigation cases in a single call. Prompts/scripts pinning
> `pacer_search` will get `ToolNotFound`; switch to `wipo_search` with `enableLitigation`.
>
> <details><summary>Earlier breaking change (0.3.0 — tool renames)</summary>
>
> | Old name (≤ 0.2.x) | New name (0.3.0+) |
> | --- | --- |
> | `google_ai_search` | `ai_search` |
> | `google_trends` | `keyword_trends` |
>
> Tool names changed to remove third-party brand references from the public MCP interface.
> Tool parameters, return shape, and pricing are unchanged.
> </details>

| | |
|---|---|
| **Version** | `0.7.3` |
| **Tools** | 18 business tools (+ a free local `pangolinfo_capabilities` introspection call) |
| **Transport** | stdio (local) · streamable HTTP (hosted — see below) |
| **Runtime** | Node.js 18+ |
| **License** | MIT |
| **Get an API key** | <https://tool.pangolinfo.com/> |

---

## Install

### Recommended: one-line installer (covers 7 AI clients)

The Pangolinfo Installer detects your AI client, writes the right config files, and you're done. Pass `--scope=mcp` to install **only** this MCP server (skip the Skills package).

**macOS / Linux**

```bash
curl -fsSL https://pangolinfo.dev/install.sh | sh -s -- \
  --agent=<your-agent> \
  --scope=mcp \
  --api-key=pgl_xxxxxxxxxxxx
```

**Windows (PowerShell)**

```powershell
irm https://pangolinfo.dev/install.ps1 | iex; `
  Install-Pangolinfo -Agent <your-agent> -Scope mcp -ApiKey pgl_xxxxxxxxxxxx
```

`<your-agent>` is one of: `claude-code`, `cursor`, `cline`, `windsurf`, `codex`, `hermes`, `openclaw`.

After the installer finishes, **restart your AI client** so it picks up the new `mcpServers` entry.

### Manual install (just download one file)

The release artifact is a **single self-contained `server.mjs`** (~800 KB) — all dependencies are bundled in. No `npm install` needed.

```bash
# macOS / Linux
mkdir -p ~/.local/lib/pangolinfo-mcp
curl -fsSL https://github.com/pangolinfo/pangolinfo-mcp/releases/latest/download/server.mjs \
  -o ~/.local/lib/pangolinfo-mcp/server.mjs
chmod +x ~/.local/lib/pangolinfo-mcp/server.mjs
```

```powershell
# Windows (PowerShell)
$dir = "$env:LOCALAPPDATA\pangolinfo-mcp"
New-Item -ItemType Directory -Force -Path $dir | Out-Null
irm https://github.com/pangolinfo/pangolinfo-mcp/releases/latest/download/server.mjs `
  -OutFile "$dir\server.mjs"
```

Then wire it into your AI client — see the per-client snippets below. Point `args` at the file you just downloaded.

> **Developers**: to build from source, `git clone` this repo and run `npm install && npm run build`. The produced `dist/server.mjs` is identical to the release asset.

---

## Get an API key

1. Sign up at <https://tool.pangolinfo.com/>
2. Copy your `pgl_xxxxxxxx` key from the dashboard
3. Top up credits if needed (each Amazon scrape call costs 0.75 credits; `pangolinfo_capabilities` is free)

---

## Manual configuration (per AI client)

Replace `/abs/path/to/pangolinfo-mcp/dist/server.mjs` with your real path, and `pgl_xxxxxxxx` with your key.

### Claude Code (`~/.claude/settings.json`)

```json
{
  "mcpServers": {
    "pangolinfo": {
      "command": "node",
      "args": ["/abs/path/to/pangolinfo-mcp/dist/server.mjs"],
      "env": { "PANGOLINFO_API_KEY": "pgl_xxxxxxxx" }
    }
  }
}
```

> Prefer `claude mcp add --scope user pangolinfo node /abs/path/to/dist/server.mjs` — it writes the same entry without hand-editing JSON.

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "pangolinfo": {
      "command": "node",
      "args": ["/abs/path/to/pangolinfo-mcp/dist/server.mjs"],
      "env": { "PANGOLINFO_API_KEY": "pgl_xxxxxxxx" }
    }
  }
}
```

### Cline (VS Code extension)

Open **Cline → MCP Servers → Edit settings JSON**, then add:

```json
{
  "mcpServers": {
    "pangolinfo": {
      "command": "node",
      "args": ["/abs/path/to/pangolinfo-mcp/dist/server.mjs"],
      "env": { "PANGOLINFO_API_KEY": "pgl_xxxxxxxx" }
    }
  }
}
```

The settings file lives at `<vscode-user>/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json`.
If you're on the standalone Cline CLI, use `~/.cline/data/settings/cline_mcp_settings.json` instead.

### Windsurf (`~/.codeium/windsurf/mcp_config.json`)

```json
{
  "mcpServers": {
    "pangolinfo": {
      "command": "node",
      "args": ["/abs/path/to/pangolinfo-mcp/dist/server.mjs"],
      "env": { "PANGOLINFO_API_KEY": "pgl_xxxxxxxx" }
    }
  }
}
```

### Codex (`~/.codex/config.toml`)

```toml
[mcp_servers.pangolinfo]
command = "node"
args = ["/abs/path/to/pangolinfo-mcp/dist/server.mjs"]

[mcp_servers.pangolinfo.env]
PANGOLINFO_API_KEY = "pgl_xxxxxxxx"
```

### Hermes (`~/.hermes/config.yaml`)

```yaml
mcp_servers:
  pangolinfo:
    command: node
    args: ["/abs/path/to/pangolinfo-mcp/dist/server.mjs"]
    env:
      PANGOLINFO_API_KEY: pgl_xxxxxxxx
```

### OpenClaw (`~/.openclaw/openclaw.json`)

```json
{
  "mcpServers": {
    "pangolinfo": {
      "command": "node",
      "args": ["/abs/path/to/pangolinfo-mcp/dist/server.mjs"],
      "env": { "PANGOLINFO_API_KEY": "pgl_xxxxxxxx" }
    }
  }
}
```

---

## Hosted (remote HTTP) — no local install

Don't want to install anything? Point your AI client at the hosted endpoint
instead of a local `server.mjs`. This is the **streamable HTTP** transport
(MCP spec), multi-tenant — you bring your own key on every request.

| | |
|---|---|
| **Endpoint** | `https://mcp.pangolinfo.com/mcp` |
| **Transport** | Streamable HTTP (POST + SSE) |
| **Auth** | Your `pgl_xxxxxxxx` key, via Bearer header **or** URL query |

### Passing your API key — two ways

**1. `Authorization` header (recommended)**

```
Authorization: Bearer pgl_xxxxxxxx
```

This is the preferred method: the key stays out of URLs, logs, and browser
history. The `Bearer` scheme is matched **case-insensitively** (`bearer`,
`BEARER`, `Bearer` all work) and extra whitespace is tolerated.

**2. `?api_key=` URL query (fallback)**

```
https://mcp.pangolinfo.com/mcp?api_key=pgl_xxxxxxxx
```

Easiest for clients that only let you paste a URL. If your key contains
URL-special characters, **URL-encode it**. The header (method 1) takes
precedence if both are supplied.

### Client config example (Claude Code / Cursor — `"url"`-style remote MCP)

```json
{
  "mcpServers": {
    "pangolinfo": {
      "url": "https://mcp.pangolinfo.com/mcp",
      "headers": { "Authorization": "Bearer pgl_xxxxxxxx" }
    }
  }
}
```

> If your client can't set headers, fall back to the URL form:
> `"url": "https://mcp.pangolinfo.com/mcp?api_key=pgl_xxxxxxxx"`.

### Notes for custom / raw HTTP integrations

If you're calling the endpoint directly (not through a standard MCP client):

- **POST** your JSON-RPC body to `/mcp`.
- The MCP streamable transport normally requires the request to advertise
  **both** `application/json` and `text/event-stream` in its `Accept` header.
  This server **backfills** the missing media type for you, so a plain
  `Accept: application/json`, `Accept: */*`, or even a missing `Accept`
  header all work — you don't need to hand-craft it.
- A `401` means the key was not found in **either** the header **or** the
  query string — check that your client actually sent it (some libraries
  drop the `Authorization` header on cross-origin redirects).

---

## Tools (18)

See [`MCP-TOOLS-MAP.md`](./MCP-TOOLS-MAP.md) for the full coordination graph (which tools chain into which).

| # | Tool | Purpose | Cost (credits) |
|---|---|---|---|
| 1 | `search_amazon` | Amazon keyword search → structured product list | 0.75 |
| 2 | `get_amazon_product` | Single-ASIN listing detail (title / bullets / features / aiReviewsSummary) | 0.75 |
| 3 | `get_amazon_reviews` | Batch reviews for an ASIN (VOC mining) | 0.75 |
| 4 | `list_bestsellers` | Amazon Bestsellers by category | 0.75 |
| 5 | `list_new_releases` | Amazon New Releases by category | 0.75 |
| 6 | `list_seller_products` | Catalog of products under one seller | 0.75 |
| 7 | `list_category_products` | All products in a category leaf | 0.75 |
| 8 | `search_categories` | Search Amazon category tree by keyword | 0.75 |
| 9 | `get_category_children` | Drill down one level in the category tree | 0.75 |
| 10 | `filter_categories` | Filter category nodes by criteria | 0.75 |
| 11 | `filter_niches` | Niche discovery (size × competition × growth) | 0.75 |
| 12 | `get_category_paths` | Resolve full ancestor paths for a category node | 0.75 |
| 13 | `search_local_maps` | Google Maps local business search | 0.75 |
| 14 | `wipo_search` | WIPO global design / trademark search (IP clearance). Set `enableLitigation=true` to also join related US patent-litigation (PACER) cases in the same call | 2 (+12 when `enableLitigation` finds a patent) |
| 15 | `ai_search` | AI Search via Google SERP (AI Overview + organic, with compliance disclaimer) | 2 |
| 16 | `keyword_trends` | Keyword Trends via Google Trends (with compliance disclaimer) | 1.5 |
| 17 | `scrape_url` | Power-user escape hatch: scrape a raw Amazon URL + parserName (non-standard pages) | 0.75 |
| 18 | `search_amazon_alexa` | Amazon Rufus AI conversational product