
SerpKite
io.github.SerpKitev1.0.0Updated Oct 5, 2026
Google search, news, maps, scholar and public webpages for AI agents, with Markdown results.
Overview
Lets an assistant run Google web, news, maps, scholar, patent, shopping, image and video searches, and convert public pages to Markdown.
- What it does
- SerpKite is a hosted remote MCP server that exposes fourteen tools: search, news, maps, scholar, patents, shopping, images, videos, autocomplete, webpage, extract, map, crawl and crawl_result. Search tools return Google results, answers, knowledge graph and related questions; webpage and extract turn public HTML or PDFs into Markdown, and extract can select passages by query. Crawl tools start a crawl of public site pages and read its status and results. Results are returned as LLM-ready Markdown.
- When to use it
- Use it when an assistant needs live Google search results, news, place data, academic papers, patents, shopping or media results, or when it must read and extract content from public web pages and sites. It is a hosted alternative to running your own search or scraping stack.
- Requirements
- A remote Streamable HTTP endpoint at reachable over the network. A SerpKite API key obtained from the provider's app site, sent in the Authorization header as Bearer followed by the key. The client must support custom headers; otherwise a Node.js-based stdio bridge is needed. No npm package is required.
Installation
In SourceWeft
- Open SerpKite in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"serpkite": {
"type": "http",
"url": "https://api.serpkite.com/v1/mcp"
}
}
}README
SerpKite MCP
Give AI agents Google search and public web content through the SerpKite remote Model Context Protocol server. Maintained by the SerpKite team.
This repository contains connection examples and registry metadata for the hosted service. The API implementation is proprietary; the documentation and configuration in this repository are MIT licensed.
Connection
- Endpoint:
https://api.serpkite.com/v1/mcp - Transport: stateless Streamable HTTP
- Authentication:
Authorization: Bearer <your-api-key> - Protocols:
2025-06-18,2025-03-26,2024-11-05
Get an API key at app.serpkite.com. Read the pricing and MCP documentation. Credits never expire; failed and empty searches are free. Set a dedicated key's monthly credit limit to control agent spending.
OAuth is planned. Clients must currently support custom headers or use the stdio bridge below. No SerpKite npm MCP package is required.
Claude Code
Cursor
Add to ~/.cursor/mcp.json or your project's .cursor/mcp.json:
VS Code
Add to .vscode/mcp.json. The password input keeps the API key out of the committed file:
Cline
Follow llms-install.md for Cline's remote connection configuration.
Claude Desktop and stdio clients
With Node.js installed, use the third-party mcp-remote bridge in your client's MCP configuration:
Keep API keys out of source control. ChatGPT connectors that only support OAuth or no authentication cannot currently connect directly.
Tools
Tool results are LLM-ready Markdown. Pricing follows the matching REST endpoints. Only public, logged-out pages are fetched. See tool inputs and costs.
Verify the connection
These metadata requests do not run searches:
The remote endpoint and all fourteen tool names were verified on 2026-10-05.
Support
Documentation · Status · [email protected]
Google is a trademark of Google LLC. SerpKite is not affiliated with Google.
Source: README.md at commit ee407da
Tools
0Version history
1- v1.0.0LatestOct 5, 2026
