SerpKite

SerpKite MCP

Give AI agents Google search, public web content, cited answers and deep research 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: OAuth 2.1 sign-in (scope mcp), or Authorization: Bearer <your-api-key>
• Protocols: 2025-06-18, 2025-03-26, 2024-11-05

Read the pricing and MCP documentation. Credits never expire; failed and empty searches are free. No SerpKite npm MCP package is required.

OAuth

The server implements the MCP authorization spec. Clients that support MCP OAuth (Claude and ChatGPT connectors, Claude Code) need only the URL: they open a SerpKite sign-in page, where you approve the connection.

• Protected resource metadata: https://api.serpkite.com/.well-known/oauth-protected-resource/v1/mcp
• Authorization server: https://app-api.serpkite.com (metadata)
• Dynamic client registration or a Client ID Metadata Document, authorization code with PKCE (S256), scopes mcp and offline_access

An approved connection runs as an API key named after the app, such as Claude (OAuth), on your API keys page. Give it a monthly credit limit, or revoke it to disconnect the app.

API key

Clients without MCP OAuth send an API key from app.serpkite.com in the Authorization header, as in the examples below. Set a dedicated key's monthly credit limit to control agent spending.

Claude Code

claude mcp add --transport http serpkite https://api.serpkite.com/v1/mcp

Run /mcp, pick serpkite and choose Authenticate to sign in with OAuth. To use an API key instead, add --header "Authorization: Bearer $SERPKITE_API_KEY".

Cursor

Add to ~/.cursor/mcp.json or your project's .cursor/mcp.json:

{
  "mcpServers": {
    "serpkite": {
      "url": "https://api.serpkite.com/v1/mcp",
      "headers": { "Authorization": "Bearer ${env:SERPKITE_API_KEY}" }
    }
  }
}

Cursor plugin

This repository is also a Cursor plugin (.cursor-plugin/plugin.json, mcp.json, a web-research skill and a rule). Set SERPKITE_API_KEY in your environment before starting Cursor; the plugin reads it through ${env:SERPKITE_API_KEY} and never stores the key.

VS Code

Add to .vscode/mcp.json. The password input keeps the API key out of the committed file:

{
  "inputs": [
    { "type": "promptString", "id": "serpkite-key", "description": "SerpKite API key", "password": true }
  ],
  "servers": {
    "serpkite": {
      "type": "http",
      "url": "https://api.serpkite.com/v1/mcp",
      "headers": { "Authorization": "Bearer ${input:serpkite-key}" }
    }
  }
}

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:

{
  "mcpServers": {
    "serpkite": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.serpkite.com/v1/mcp", "--header", "Authorization: Bearer ${SERPKITE_API_KEY}"],
      "env": { "SERPKITE_API_KEY": "YOUR_API_KEY" }
    }
  }
}

Keep API keys out of source control.

ChatGPT

With developer mode enabled, create a connector with the URL https://api.serpkite.com/v1/mcp and OAuth authentication. ChatGPT registers itself and sends you to the SerpKite approval page.

Tools

Tool	Purpose
search	Google web results, answers, knowledge graph and related questions
news	Google News articles
maps	Places, ratings, addresses and coordinates
place	One place's details: address, hours, phones, time zone (by place_id, cid or fid from maps)
scholar	Academic papers, citations and PDF links
patents	Patent search
shopping	Products, prices and merchants
images	Image search
videos	Video search
autocomplete	Query suggestions
webpage	Public HTML or PDF to Markdown
answer	Answer a question from live Google results with numbered citations
extract	Read up to 20 URLs; optional query passages, summary or JSON matching your schema
map	Discover a site's URLs
crawl	Start a crawl of public site pages
crawl_result	Read crawl status and results
research	Start an async deep-research task that ends in a cited Markdown report
research_result	Read research status and the report

Tool results are LLM-ready Markdown. Pricing follows the matching REST endpoints; a failed answer or AI step is free, and research is charged only when the report is written. Only public, logged-out pages are fetched. See tool inputs and costs.

Verify the connection

These metadata requests do not run searches:

curl https://api.serpkite.com/v1/mcp \
  -H "Authorization: Bearer $SERPKITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"1.0"}}}'

curl https://api.serpkite.com/v1/mcp \
  -H "Authorization: Bearer $SERPKITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list"}'

The remote endpoint and all eighteen tool names were verified on 2026-10-24.

Support

Documentation · Status · [email protected]

Google is a trademark of Google LLC. SerpKite is not affiliated with Google.