{% endstep %}
{% step %}
### Use the following endpoint to connect to a remote MCP server.
```
{
"mcpServers": {
"talordata": {
"type": "http",
"url": "https://mcp.talordata.net/YOUR_API_TOKEN/mcp"
}
}
}
```
{% endstep %}
{% endstepper %}
### Authentication
Supports three methods:
1. **Path-based (Recommended):** /{YOUR\_API\_TOKEN}/mcp
2. **Authorization Header:** Authorization: Bearer YOUR\_API\_TOKEN
3. **Custom Headers:** X-Talor-Serp-Token: YOUR\_API\_TOKEN
> Example:
#### **Path-based**
```
curl "https://mcp.talordata.net/your_token/mcp" -d '...'
```
#### Authorization Header
```
curl "https://mcp.talordata.net/mcp" -H "Authorization: Bearer your_token" -d '...'
```
#### **Custom Headers**
```
curl "https://mcp.talordata.net/mcp" -H "X-Talor-Serp-Token: your_token" -d '...'
```
{% hint style="info" %}
Note: The GET / and GET /healthz endpoints do not require authentication.
{% endhint %}
### Tools
#### **1.list\_engines**
Lists all supported search engines, categories, and resource URIs.
\
Parameters: None
Example: {"name": "list\_engines"}
#### **2.search**
Execute a SERP search request. Consult the resources located under `talor://engines` to review the specific parameters for each engine before invoking this tool.
Parameters:
engine (Optional): Engine identifier, e.g., google, google\_images, bing\_images, duckduckgo.
If not provided, use the `engine` field in `params` or the default engine.
params (Required): An engine-specific parameter object; it must match the Schema resource definition of the corresponding engine.
json (Optional): Upstream response format. json->1, json\_html->2, html->3.
response\_mode (Optional): complete returns a complete response, compact removes common metadata fields. Default: complete
Supported Search Engines (33 total):
Google (25)
Search, Finance, Finance Markets, Flights, Hotels, Images, Jobs, Lens, Local, Maps, News, Patents, Patents Details, Play Search, Play Books, Play Games, Play Movies, Play Product, Scholar, Scholar Author, Scholar Cite, Shopping, Trends, Videos, Web
Bing (6)
Search, Images, Maps, News, Shopping, Videos
Yandex (1)
Search
DuckDuckGo (1)
Search
> Example:
```
{"name": "search", "arguments": {"engine": "google", "params": {"q": "coffee shops", "location": "Austin, TX"}}}
{"name": "search", "arguments": {"engine": "google", "params": {"q": "weather in London"}}}
{"name": "search", "arguments": {"engine": "google", "params": {"q": "AAPL stock"}}}
{"name": "search", "arguments": {"engine": "duckduckgo", "params": {"q": "car"}}}
{"name": "search", "arguments": {"engine": "bing", "params": {"q": "latest news"}, "response_mode": "compact"}}
```
Result Types: Answer Box, Organic Results, News, Images, Shopping, Knowledge Cards—automatically detected and formatted by upstream APIs.
#### **3.history**
Query SERP usage history.
\
Parameters:
page (Optional): Page number, default 1
page\_size (Optional): Page Size (Common values: 20, 50, 100)
search\_query(Optional): Filter by Search Keywords
search\_engine (Optional): Filter by Search Engine Display Name
status (Optional): Status Filter. Possible values: all, success, error
start\_time (Optional): Start Time (Unix Timestamp, seconds)
end\_time (Optional): End Time (Unix Timestamp, seconds)
timezone (Optional): Time zone, e.g., Asia/Shanghai or +08:00
> Example:
```
{"name": "history", "arguments": {"page": 1, "page_size": 20}}
{"name": "history", "arguments": {"search_query": "coffee", "status": "success"}}
{"name": "history", "arguments": {"start_time": 1700000000, "end_time": 1700100000, "timezone": "Asia/Shanghai"}}
```
#### **4.statistics**
Query SERP usage statistics.
\
Parameters:
start\_date (Required): Start Date (YYYY-MM-DD format)
end\_date (Required): End date, format YYYY-MM-DD
engines (Optional): Engine filter; a comma-separated string or an array of strings.
timezone (Optional): Time zone offset, e.g., +00:00, +08:00, -05:00
> Example:
```
{"name": "statistics", "arguments": {"start_date": "2025-01-01", "end_date": "2025-01-31"}}
{"name": "statistics", "arguments": {"start_date": "2025-01-01", "end_date": "2025-01-31", "engines": "google,bing"}}
{"name": "statistics", "arguments": {"start_date": "2025-01-01", "end_date": "2025-01-31", "timezone": "+08:00"}}
```
### MCP Resources
* Indexed Resources: talor://engines
Returns a list of all engines, their categories, and resource URIs.
* Engine Schema Resources: talor://engines/{engine\_key}
Returns the complete parameter schema definition for a specific engine, used to understand the available parameters before invoking the search tool.
### HTTP Routing
1. GET / Return Basic Service Information (No Authentication Required)
2. GET /healthz Health Check (No Authentication Required)
3. POST /mcp MCP Protocol Endpoint (Authentication Required)
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.talordata.com/serp-api/mcp-server/quick-start.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.