Bocha Search

🚀 Bocha Search MCP Server

Bocha Search MCP Server is a search engine designed for AI, enabling AI applications to access high - quality world knowledge from nearly tens of billions of web pages and ecological content sources, covering multiple fields such as weather, news, encyclopedias, healthcare, train tickets, and images.

📋 Version Information

v1

📄 Product Description

Short Description

Bocha is a search engine specifically designed for AI, allowing your AI applications to access high - quality world knowledge from nearly tens of billions of web pages and ecological content sources, covering multiple fields such as weather, news, encyclopedias, healthcare, train tickets, and images.

Long Description

Bocha is a search engine specifically designed for AI, enabling your AI applications to obtain high - quality world knowledge from nearly tens of billions of web pages and ecological content sources, spanning various fields including weather, news, encyclopedias, healthcare, train tickets, and images.

🗂️ Classification

Web Search

🏷️ Tags

Search, News, Weather, Encyclopedia

🛠️ Tools

Tool1: Bocha Web Search

Detailed Description

Search for information and web links across the entire network on Bocha. The returned results include the web page title, web URL, web page summary, publication time, website name, website icon, image link, etc.

Parameters Required for Debugging

Input:

• query: Search term (required)
• freshness: Search within a specified time range (optional values: YYYY - MM - DD, YYYY - MM - DD..YYYY - MM - DD, noLimit, oneYear, oneMonth, oneWeek, oneDay. Default is noLimit)
• count: Number of returned results (range 1 - 50)

Output:

• The results include web page titles, URLs, summaries, publication times, website names, icon links, and image links, supporting a maximum of 50 results.

Tool2: Bocha AI Search

Detailed Description

Based on Bocha Web Search, Bocha AI Search uses AI to recognize the semantics of search terms and additionally returns structured modal cards for vertical domain content, such as dozens of types including weather cards, calendar cards, and encyclopedia cards. It performs better in semantic recognition, search result timeliness, and content richness.

Parameters Required for Debugging

Input:

• query: Search term (required)
• freshness: Time range (optional values: YYYY - MM - DD, YYYY - MM - DD..YYYY - MM - DD, noLimit, oneYear, oneMonth, oneWeek, oneDay. Default is noLimit)
• count: Number of returned results (range 1 - 50)

Output:

• The results include web page information and structured modal cards, such as those for weather, encyclopedias, healthcare, perpetual calendars, trains, constellations, precious metals, exchange rates, oil prices, mobile phones, stocks, cars, etc.

❓ Frequently Asked Questions

What functions can the Bocha Web Search service provide?

Bocha Web Search offers general search capabilities across the entire network. You can obtain information and web links from the whole network through Bocha. The returned results include web page titles, URLs, summaries, website names, icons, publication times, image links, etc., with a maximum of 50 results per search.

Traditional search engines use a search algorithm based on keywords + bid - ranking mechanisms, aiming to attract users to click for advertising revenue. In contrast, Bocha is based on multi - modal hybrid search and semantic ranking technology, supporting natural language search methods for AI application scenarios and focusing on providing clean, accurate, and high - quality answers.

Bocha's semantic ranking technology uses the Transformer architecture to rank search results based on their semantic relevance to the user's question. Since large models also use the Transformer architecture and make selections by judging the semantic relevance between context and the user's question, large models are more likely to choose the search results provided by Bocha.

Currently, Bocha's search performance is the closest to the Bing Search API among domestic search engines. Due to the fact that Bing Search API data goes overseas (no domestic region), it is expensive ($15 per thousand queries), and it does not provide text summaries (only a 50 - 100 - word snippet), many domestic enterprise customers have switched from Bing to Bocha.

What functions can the Bocha AI Search service provide?

Based on Bocha Web Search, Bocha AI Search uses AI to recognize the semantics of search terms and additionally returns structured modal cards for vertical domain content, such as dozens of types including weather cards, calendar cards, and encyclopedia cards. It performs better in semantic recognition, search result timeliness, and content richness.

Currently supported modal card types include: weather, encyclopedias, healthcare, perpetual calendars, trains, constellations, precious metals, exchange rates, oil prices, mobile phones, stocks, cars, etc.

Taking stock information as an example, real - time stock data is generally not available on web pages and requires structured modal cards for support. The Bocha AI Search API can output structured data modal cards for stock prices in addition to web page information. Through the structured data provided by the modal cards, the accuracy of answers to timeliness - related questions in AI applications can be further enhanced.