# SerpMCP

<!-- mcp-name: io.github.AceDataCloud/mcp-serp -->

[![PyPI version](https://img.shields.io/pypi/v/mcp-serp.svg)](https://pypi.org/project/mcp-serp/)
[![PyPI downloads](https://img.shields.io/pypi/dm/mcp-serp.svg)](https://pypi.org/project/mcp-serp/)
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![MCP](https://img.shields.io/badge/MCP-Compatible-green.svg)](https://modelcontextprotocol.io)

A [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server for Google search using [SERP API](https://platform.acedata.cloud/documents/serp-google?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_documents_serp-google) through the [AceDataCloud API](https://platform.acedata.cloud?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_platform).

Perform Google searches and get structured results directly from Claude, VS Code, or any MCP-compatible client.

## Features

- **Web Search** - Regular Google web search with structured results
- **Image Search** - Search for images with URLs and thumbnails
- **News Search** - Get latest news articles on any topic
- **Video Search** - Find videos from YouTube and other sources
- **Places Search** - Search for local businesses and places
- **Maps Search** - Find locations and geographic information
- **Knowledge Graph** - Get structured entity information
- **Localization** - Support for multiple countries and languages
- **Time Filtering** - Filter results by time range

## Tool Reference

| Tool | Description |
|------|-------------|
| `serp_google_search` | Search Google and get structured results using the SERP API. |
| `serp_google_images` | Search Google Images and get image results. |
| `serp_google_news` | Search Google News and get news article results. |
| `serp_google_videos` | Search Google Videos and get video results. |
| `serp_google_places` | Search Google for local places and businesses. |
| `serp_google_maps` | Search Google Maps for locations. |
| `serp_list_search_types` | List all available Google search types. |
| `serp_list_countries` | List commonly used country codes for Google search. |
| `serp_list_languages` | List commonly used language codes for Google search. |
| `serp_list_time_ranges` | List available time range filters for Google search. |
| `serp_get_usage_guide` | Get a comprehensive guide for using the Google SERP tools. |

## Connect: hosted OAuth, API token, or local stdio

The hosted endpoint is `https://serp.mcp.acedata.cloud/mcp`. Choose one route for the MCP client:

| Route | When to use it | Credential setup |
|---|---|---|
| Hosted OAuth | The client supports remote MCP OAuth | Add only the URL, then sign in to AceDataCloud and approve access. No token needs to be pasted into client configuration. |
| Hosted API token | The client cannot finish OAuth, or you need an explicit integration credential | Send an AceDataCloud API token in the `Authorization: Bearer …` header. Keep it in a local secret store or environment variable. |
| Local stdio | The client runs a local MCP process | Install `mcp-serp` and pass `ACEDATACLOUD_API_TOKEN` to that process. It still calls the AceDataCloud API. |

The hosted service advertises OAuth metadata and Dynamic Client Registration (DCR). **DCR registers the client application; it is not an API key.** OAuth signs you in and the client sends the resulting Bearer token; it may reuse or create an API credential for the account. Browser sign-in still requires an AceDataCloud account. The hosted service can be metered: review [current service documentation](https://platform.acedata.cloud/documents/serp-mcp?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_quick_start) and displayed pricing before a real operation. Do not configure both an OAuth login and a fixed `Authorization` header for the same server.

### Hosted OAuth examples

- **Claude and Claude Desktop chat:** Add a remote custom connector in `Customize → Connectors → Add custom connector`, enter `https://serp.mcp.acedata.cloud/mcp`, select sign-in, and choose **Register automatically** if Claude asks how to register its OAuth client. Complete consent. Claude Desktop's local `claude_desktop_config.json` is a separate setup. [Claude connector guide](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp).
- **Claude Code:** `claude mcp add --transport http --scope user serp https://serp.mcp.acedata.cloud/mcp`, then start `claude`, open `/mcp`, and authenticate the Serp server. [Claude Code MCP guide](https://code.claude.com/docs/en/mcp).
- **Cursor:** Add a remote server with only `https://serp.mcp.acedata.cloud/mcp`. For a project, merge the entry below into `<project>/.cursor/mcp.json`; for personal use, use `~/.cursor/mcp.json`. [Cursor MCP guide](https://cursor.com/docs/mcp).
- **VS Code / Copilot:** Run **MCP: Add Server**, select HTTP, enter `https://serp.mcp.acedata.cloud/mcp`, then finish the browser sign-in. New portable workspace configs use `<project>/.mcp.json`; the VS Code-specific format below uses `<project>/.vscode/mcp.json` or the user profile. Check **MCP: List Servers**. [VS Code MCP setup](https://code.visualstudio.com/docs/agent-customization/mcp-servers).
- **Codex:** `codex mcp add serp --url https://serp.mcp.acedata.cloud/mcp`, then `codex mcp login serp`. Its user settings are in `~/.codex/config.toml`. [Official Codex MCP guide](https://developers.openai.com/codex/mcp/).

Cursor project config (OAuth):

```json
{
  "mcpServers": {
    "serp": {"url": "https://serp.mcp.acedata.cloud/mcp"}
  }
}
```

VS Code-specific workspace config (OAuth):

```json
{
  "servers": {
    "serp": {"type": "http", "url": "https://serp.mcp.acedata.cloud/mcp"}
  }
}
```

### Hosted API token

<!-- BEGIN TOKEN ONBOARDING -->
1. Open [Ace Data Cloud → Applications](https://platform.acedata.cloud/console/applications?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_api_key). Sign in, or register an account first.
2. Find **General application**. If it has not been created, choose **Initialize General Application**. A general key can use the services available to your account; a dedicated application's key is limited to its service. Check the required service/model access and [current pricing](https://platform.acedata.cloud/models?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_models).
3. Copy the **API Key** from the application card, or open **Keys / Manage Keys → Create** to create a separate key for this integration. Give it a recognizable name so you can revoke or rotate it independently.
4. When creating a key, review **Expiration Time**, **Set Usage Limitation**, and **Allowed APIs**. Enable only the restrictions you need, allow the operations you will call, then click **Create** and copy the token from the key list. Task lookup does not grant permission to submit a generation. Confirm the application's balance can cover your first request; any trial allowance is whatever your account currently displays.
5. Copy only the token value, without quotation marks, spaces, or `Bearer `. An API Key / API Token field expects this raw value; only a manually configured HTTP `Authorization` header needs the `Bearer ` prefix. A `platform-...` account-management token cannot replace a generation API key.

![Copy an application API key or open Manage Keys](https://raw.githubusercontent.com/AceDataCloud/NanoBananaDify/2522b2f57210597af2db866445319334a1677a23/_assets/tutorial/get-api-key-en.png)

![Create a separately named key with optional restrictions](https://raw.githubusercontent.com/AceDataCloud/NanoBananaDify/2522b2f57210597af2db866445319334a1677a23/_assets/tutorial/create-api-key-en.png)

Save the key in the client's credential store or the environment variable shown below. Never put it in a prompt, shared workflow, screenshot, or Git commit. If authentication fails, check the full copied value, application/service access, expiration, usage limit, and balance before creating another key.
<!-- END TOKEN ONBOARDING -->

A fixed Bearer header bypasses OAuth. If the header is invalid, remove it before trying browser sign-in; keep the saved credential private.

For Claude Code, the shell expands the token when you add the server; treat the saved user MCP config as a secret:

```bash
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
claude mcp add --transport http --scope user serp https://serp.mcp.acedata.cloud/mcp \
  --header "Authorization: Bearer $ACEDATACLOUD_API_TOKEN"
```

For a Claude Code project config, put a variable reference in `<project>/.mcp.json` and set that variable in the environment that launches Claude Code:

```json
{
  "mcpServers": {
    "serp": {
      "type": "http",
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${ACEDATACLOUD_API_TOKEN}"}
    }
  }
}
```

Cursor uses a different environment-variable syntax in `~/.cursor/mcp.json` or an uncommitted project config:

```json
{
  "mcpServers": {
    "serp": {
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${env:ACEDATACLOUD_API_TOKEN}"}
    }
  }
}
```

In VS Code, run **MCP: Open User Configuration** and merge this server plus its masked input; `${input:...}` is for VS Code's user/workspace format and is not portable to the Agent Host `.mcp.json` format:

```json
{
  "inputs": [
    {"id": "acedata-serp-token", "type": "promptString", "description": "AceDataCloud API token", "password": true}
  ],
  "servers": {
    "serp": {
      "type": "http",
      "url": "https://serp.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${input:acedata-serp-token}"}
    }
  }
}
```

For **Cline**, use its MCP configuration UI or CLI file `~/.cline/data/settings/cline_mcp_settings.json`; its remote transport value is `streamableHttp`. For **JetBrains AI Assistant**, add a remote URL from **Settings → Tools → AI Assistant → Model Context Protocol (MCP)**. For **Zed**, use a `context_servers` entry with the URL only for OAuth or add a local Bearer header. These clients have different configuration schemas; follow their current UI rather than copying another client's JSON. [Cline](https://docs.cline.bot/mcp/mcp-overview) · [JetBrains](https://www.jetbrains.com/help/ai-assistant/mcp.html) · [Zed](https://zed.dev/docs/ai/mcp).

### Local stdio

Install the package and give the local process an API token:

```bash
python -m pip install mcp-serp
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
mcp-serp
```

For Claude Desktop local MCP, merge this entry into the file opened by its developer settings (`~/Library/Application Support/Claude/claude_desktop_config.json` on macOS). `uvx` requires [uv](https://docs.astral.sh/uv/) on `PATH`:

```json
{
  "mcpServers": {
    "serp": {
      "command": "uvx",
      "args": ["mcp-serp"],
      "env": {"ACEDATACLOUD_API_TOKEN": "YOUR_API_TOKEN"}
    }
  }
}
```

Keep this user-level file private. Self-hosted HTTP uses `mcp-serp --transport http --port 8000`; expose it only with suitable network and TLS controls. Local execution still calls the AceDataCloud API.

### Check before using the service

1. `https://serp.mcp.acedata.cloud/health` returning `{"status":"ok"}` checks endpoint reachability only.
2. Confirm that the MCP client loads tools. `serp_list_search_types` and `serp_get_usage_guide` are local reference tools with no search API charge; they do not verify downstream API access or balance. Search tools are read-only but consume Credits, and repeating a search can incur another charge.
3. If you need a full API check, call `serp_google_search` with your own valid input after reviewing [current service documentation](https://platform.acedata.cloud/documents/serp-mcp?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_quick_start) and displayed pricing.

For **401**, check which auth route the client used and whether the token or OAuth session is valid. A **403** may mean an account permission or content moderation failure; read the returned error. Insufficient balance and downstream service failures need their own diagnosis. A listed tool or submitted task does not prove a successful result.

## Available Tools

### Search Tools

| Tool                 | Description                             |
| -------------------- | --------------------------------------- |
| `serp_google_search` | Flexible Google search with all options |
| `serp_google_images` | Search for images                       |
| `serp_google_news`   | Search for news articles                |
| `serp_google_videos` | Search for videos                       |
| `serp_google_places` | Search for local places/businesses      |
| `serp_google_maps`   | Search for map locations                |

### Information Tools

| Tool                     | Description                          |
| ------------------------ | ------------------------------------ |
| `serp_list_search_types` | List available search types          |
| `serp_list_countries`    | List country codes for localization  |
| `serp_list_languages`    | List language codes for localization |
| `serp_list_time_ranges`  | List time range filter options       |
| `serp_get_usage_guide`   | Get comprehensive usage guide        |

## Usage Examples

### Basic Web Search

```
User: Search for information about artificial intelligence

Claude: I'll search for information about AI.
[Calls serp_google_search with query="artificial intelligence"]
```

### News Search with Time Filter

```
User: What's the latest news about technology?

Claude: I'll search for recent tech news.
[Calls serp_google_news with query="technology", time_range="qdr:d"]
```

### Localized Search

```
User: Find popular restaurants in Tokyo

Claude: I'll search for restaurants in Tokyo.
[Calls serp_google_places with query="popular restaurants Tokyo", country="jp"]
```

### Image Search

```
User: Find images of the Northern Lights

Claude: I'll search for aurora borealis images.
[Calls serp_google_images with query="Northern Lights aurora borealis"]
```

## Search Parameters

### Search Types

| Type     | Description                  |
| -------- | ---------------------------- |
| `search` | Regular web search (default) |
| `images` | Image search                 |
| `news`   | News articles                |
| `maps`   | Map results                  |
| `places` | Local businesses             |
| `videos` | Video results                |

### Time Range Filters

| Code    | Time Range |
| ------- | ---------- |
| `h`     | Past hour  |
| `qdr:h` | Past hour  |
| `d`     | Past day   |
| `qdr:d` | Past day   |
| `w`     | Past week  |
| `qdr:w` | Past week  |
| `m`     | Past month |
| `qdr:m` | Past month |
| `y`     | Past year  |
| `qdr:y` | Past year  |

### Image Size Filters (for `images` search type)

`large`, `medium`, `icon`, `2mp`, `4mp`, `6mp`, `8mp`, `10mp`, `12mp`, `15mp`, `20mp`, `40mp`, `70mp`

### Common Country Codes

| Code | Country        |
| ---- | -------------- |
| `us` | United States  |
| `uk` | United Kingdom |
| `cn` | China          |
| `jp` | Japan          |
| `de` | Germany        |
| `fr` | France         |

### Common Language Codes

| Code    | Language             |
| ------- | -------------------- |
| `en`    | English              |
| `zh-cn` | Chinese (Simplified) |
| `ja`    | Japanese             |
| `es`    | Spanish              |
| `fr`    | French               |
| `de`    | German               |

## Response Structure

### Regular Search Results

- **knowledge_graph**: Entity information (company, person, etc.)
- **answer_box**: Direct answers
- **organic**: Regular search results with title, link, snippet
- **people_also_ask**: Related questions
- **related_searches**: Related queries

### Image Search Results

- **images**: Image results with URLs and thumbnails

### News Search Results

- **news**: News articles with source and date

## Configuration

### Environment Variables

| Variable                    | Description                 | Default                     |
| --------------------------- | --------------------------- | --------------------------- |
| `ACEDATACLOUD_API_TOKEN`    | API token from AceDataCloud | **Required**                |
| `ACEDATACLOUD_API_BASE_URL` | API base URL                | `https://api.acedata.cloud` |
| `ACEDATACLOUD_OAUTH_CLIENT_ID`  | OAuth client ID (hosted mode) | —                           |
| `ACEDATACLOUD_PLATFORM_BASE_URL` | Platform base URL            | `https://platform.acedata.cloud` |
| `SERP_REQUEST_TIMEOUT`      | Request timeout in seconds  | `30`                        |
| `LOG_LEVEL`                 | Logging level               | `INFO`                      |

### Command Line Options

```bash
mcp-serp --help

Options:
  --version          Show version
  --transport        Transport mode: stdio (default) or http
  --port             Port for HTTP transport (default: 8000)
```

## Development

### Setup Development Environment

```bash
# Clone repository
git clone https://github.com/AceDataCloud/SerpMCP.git
cd SerpMCP

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # or `.venv\Scripts\activate` on Windows

# Install with dev dependencies
pip install -e ".[dev,test]"
```

### Run Tests

```bash
# Run unit tests
pytest

# Run with coverage
pytest --cov=core --cov=tools

# Run integration tests (requires API token)
pytest tests/test_integration.py -m integration
```

### Code Quality

```bash
# Format code
ruff format .

# Lint code
ruff check .

# Type check
mypy core tools
```

### Build & Publish

```bash
# Install build dependencies
pip install -e ".[release]"

# Build package
python -m build

# Upload to PyPI
twine upload dist/*
```

## Project Structure

```
SerpMCP/
├── core/                   # Core modules
│   ├── __init__.py
│   ├── client.py          # HTTP client for SERP API
│   ├── config.py          # Configuration management
│   ├── exceptions.py      # Custom exceptions
│   └── server.py          # MCP server initialization
├── tools/                  # MCP tool definitions
│   ├── __init__.py
│   ├── search_tools.py    # Search tools
│   └── info_tools.py      # Information tools
├── prompts/                # MCP prompt templates
│   └── __init__.py
├── tests/                  # Test suite
│   ├── conftest.py
│   ├── test_client.py
│   └── test_config.py
├── deploy/                 # Deployment configs
│   └── production/
│       ├── deployment.yaml
│       ├── ingress.yaml
│       └── service.yaml
├── .env.example           # Environment template
├── .gitignore
├── CHANGELOG.md
├── Dockerfile             # Docker image for HTTP mode
├── docker-compose.yaml    # Docker Compose config
├── LICENSE
├── main.py                # Entry point
├── pyproject.toml         # Project configuration
└── README.md
```

## API Reference

This server wraps the [AceDataCloud Google SERP API](https://platform.acedata.cloud/documents/serp-google?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_documents_serp-google):

- [Google SERP API Documentation](https://platform.acedata.cloud/documents/serp-google?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_documents_serp-google)

## Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch (`git checkout -b feature/amazing`)
3. Commit your changes (`git commit -m 'Add amazing feature'`)
4. Push to the branch (`git push origin feature/amazing`)
5. Open a Pull Request

## Documentation

<!-- canonical-documentation -->
[Documentation](https://platform.acedata.cloud/documents/serp-mcp?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_quick_start)

## License

MIT License - see [LICENSE](LICENSE) for details.

## Links

- [AceDataCloud Platform](https://platform.acedata.cloud?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_platform)
- [Google SERP API](https://platform.acedata.cloud/documents/serp-google?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_documents_serp-google)
- [Model Context Protocol](https://modelcontextprotocol.io)
- [MCP Python SDK](https://github.com/modelcontextprotocol/python-sdk)

---

Made with love by [AceDataCloud](https://platform.acedata.cloud?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=serp_mcp_readme_platform)