io.github.serpapiPublished by GitHub account serpapiv2.2.0Updated Nov 4, 2026
Official SerpApi MCP server for Google, Bing, and other search engines.
Official SerpApi MCP server that gives an assistant live search-engine results across many engines plus web page extraction and crawling.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.serpapi%2Fserpapi-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"serpapi": {
"type": "http",
"url": "https://mcp.serpapi.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}A Model Context Protocol (MCP) server implementation that integrates with SerpApi for comprehensive search engine results and data extraction.
[Python 3.13+] [MIT License] [Install in VS Code] [Install in Cursor]
search_table and search_dashboard tools that render results as an interactive UI in supporting hosts.mcpb), see belowSerpApi MCP Server is available as a hosted service at mcp.serpapi.com. In order to connect to it, you need to provide an API key. You can find your API key on your SerpApi dashboard.
You can configure Claude Desktop to use the hosted server:
You can also add the hosted server to these MCP clients:
OpenClaw
Claude Code
Hermes
Codex (reads the key from SERPAPI_API_KEY in your shell)
Configure Claude Desktop:
Get your API key: serpapi.com/manage-api-key
For a local, one-click install, download the .mcpb bundle from the latest release and open it with Claude Desktop (or drop it onto Settings → Extensions). Claude Desktop asks for your SerpApi API key during install, stores it as a sensitive setting, and runs the server locally over stdio. It provisions Python and dependencies with uv at install time. The same bundle works on macOS, Windows and Linux.
The same stdio entry point works with any local MCP host that launches servers as a subprocess:
Two methods are supported:
Authorization: Bearer YOUR_API_KEY (recommended: the key stays out of URLs and logs)/YOUR_API_KEY/mcp, for clients that cannot set headersExamples:
No key is needed to connect, list tools or read resources. search and the App tools need one and return an error without it.
The MCP server has one main search tool that supports all SerpApi engines and result types. You can find all available parameters on the SerpApi API reference.
Engine parameter schemas are also exposed as MCP resources: serpapi://engines (index) and serpapi://engines/<engine>.
Clients that support argument completion can request engine-name suggestions for serpapi://engines/{engine_name}. For example, the prefix google_f suggests matching engine identifiers. This completes the resource URI parameter, not arbitrary search queries.
The parameters you can provide are specific for each API engine. Some sample parameters are provided below:
params.q (required): Search queryparams.engine: Search engine (default: "google_light")params.location: Geographic filterparams.output: Response format; omit for JSON (default), or set to "md" for Markdownmode: Response mode; "compact" removes metadata from JSON, while Markdown is returned unchangedExamples:
Supported engines: Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and more (see serpapi://engines).
Result types: Answer boxes, organic results, news, images, shopping - automatically detected and formatted.
Search responses preserve the existing MCP structuredContent.result string and include the same string in text content. For JSON output, result contains serialized JSON; existing clients can continue parsing it with JSON.parse(response.structuredContent.result). For Markdown output, it contains the unchanged Markdown. Errors and cancellations use the same wrapper. Search execution failures set isError: true; clients using FastMCP's high-level call_tool() should handle ToolError, or use call_tool_mcp() to inspect the result flag. See MCP tool results.
search uses the engine catalog and engine-specific rules to identify missing parameters. Supporting MCP 2026-07-28 clients receive a form before any search runs. Accepted answers are validated; decline or cancellation runs no search. Legacy clients and clients without form elicitation receive an error listing the missing parameters so the agent can ask in conversation. See MCP input requests.
selected_flights_json retain their existing behavior.search_query, Yelp's find_loc, and Amazon's k. Engine rules account for known defaults and alternatives, including Amazon category nodes, eBay categories, and Google Scholar citation searches.If an answer introduces another requirement, the tool lists the remaining fields for the agent to supply in a new call. Forms support strings, numbers, booleans, and single-choice fields; unsupported complex fields receive the missing-parameter error. Unknown engines pass through to SerpApi.
The extract tool reads web pages and returns their content as structured JSON or Markdown. You can extract a single page, discover a website's URLs, or crawl multiple pages. Find all available parameters on the Extract API reference or in the serpapi://engines/extract resource.
Some parameters you can provide:
params.url (required): Page or website URLparams.mode: Extraction mode; "scrape" (default) reads one page, "map" discovers URLs, and "crawl" extracts multiple pagesparams.include_markdown: Include the page's content as Markdown; defaults to true for scrape and crawl, or set to false to disable itparams.output: Response format; defaults to "json" in complete mode and "md" in compact mode. Set it explicitly to override the format.params.max_pages: Maximum pages to crawl, including the starting page (default: 10, maximum: 100)params.json_restrictor: Choose which fields to return, such as "markdown,error"mode: Response mode; "complete" (default) returns the full response. "compact" defaults to native Markdown. With an explicit params.output="json", single-page compact extraction keeps the top-level markdown field when present and retains API errors. Responses without Markdown, including results redirected to another engine, keep their data with metadata removed. Explicit params.json_restrictor values and params.include_markdown=false take precedence when using JSON. For map and crawl, compact JSON removes metadata. Markdown output is returned unchanged.Examples:
For a single page's content as native Markdown, use mode="compact". Add params.output="json" to receive JSON containing the markdown field instead. Complete JSON includes that field by default; crawl JSON includes it in each pages entry. Setting params.output="json" and params.include_markdown=false keeps the remaining structured fields without Markdown.
Crawling consumes one search credit per successfully extracted page on an uncached request. Use params.max_pages to limit how many pages are extracted.
The search tool returns JSON by default. For hosts that support the MCP Apps extension (SEP-1865), two opt-in tools render results as an interactive UI directly in the conversation, so the bulk SERP JSON never enters the model's context window:
search_table: organic results as a sortable, searchable table.search_dashboard: summary metrics, a source-breakdown chart, and a results table with a click-to-expand detail panel.Both accept the same params as search. Hosts that don't support MCP Apps simply ignore these tools.
/{YOUR_KEY}/mcp or header Bearer YOUR_KEYserpapi.com with your API key; results come back unchanged. See the SerpApi Privacy Policy for how SerpApi handles searches and accounts.mcp.serpapi.com records request metrics (method, status code, duration) and stores no queries or results. A key in the URL path can appear in request logs, so prefer the header.serpapi.com directly. Nothing passes through mcp.serpapi.com.See CONTRIBUTING.md for development setup, schema refresh commands, testing, Docker and MCP Bundle builds, and releases.
MIT License - see LICENSE file for details.
Source: README.md at commit 6ffa961
SerpApi search (dashboard)
Interactive dashboard variant of `search`: returns summary metrics, a source breakdown chart, and a results table with a click-to-expand detail panel, all rendered in the conversation. Same params as `search`. Use for a richer visual overview of a query's results. Automatically selects an engine-specific dashboard when available (e.g. google_flights gets price intelligence charting).
paramsSerpApi search (table)
Interactive UI variant of `search`: returns organic results as a sortable, searchable table rendered in the conversation. Same params as `search`. Use when the host supports MCP Apps and the user wants to browse results visually rather than read JSON.
paramsSerpApi extract
Extract content from a public http(s) URL, discover site URLs, or crawl pages. API options go in params: url is required; params.mode is scrape (default), map, or crawl. See serpapi://engines/extract for all options. Top-level mode controls the response: - complete (default): full JSON. - compact: native Markdown by default. params.output selects the format and overrides either default: - "md": return native Markdown unchanged in either response mode. - "json": return JSON, with filtering determined by the response mode. Compact JSON removes metadata. For scrape responses containing markdown, it also keeps only markdown and any error field. include_markdown=false or an explicit json_restrictor skips this extra filtering. Map/crawl and responses without markdown keep their remaining fields. Use complete with output="json" for full JSON. Crawl max_pages defaults to 10 (maximum 100). Each successfully extracted, uncached page consumes one credit. Examples: Full scrape JSON: {"params":{"url":"https://example.com"},"mode":"complete"} Scrape Markdown: {"params":{"url":"https://example.com"},"mode":"compact"} Map URLs as JSON: {"params":{"url":"https://example.com","mode":"map"},"mode":"complete"} Crawl pages as Markdown: {"params":{"url":"https://example.com","mode":"crawl","max_pages":2},"mode":"compact"}
modeparamsSerpApi search
Universal search tool supporting all SerpApi engines and result types. When to use: - Any query needing live, structured SERP data: web results, news, product listings, job postings, local businesses, flight/hotel prices, video results, images, stock/weather cards, knowledge graph entities. Engine discovery via MCP resources: - serpapi://engines lists all engines supported by this tool. - serpapi://engines/<engine> provides engine-specific parameters and supported options. - Example: serpapi://engines/google_news Input schema: params: JSON object containing SerpApi engine parameters. Common parameters: - q: Search query. Required for most engines. - engine: SerpApi engine name. Defaults to "google_light". - location: Optional geographic location for localized results. - output: Optional response format. Omit for JSON (default), or set to "md" for Markdown. Engine-specific parameters are available via MCP resources: - serpapi://engines lists all supported engines. - serpapi://engines/<engine> provides parameters and options for one engine. mode: Response mode. Defaults to "complete". - "complete": Return the full SerpApi response. - "compact": Remove metadata fields from JSON responses. Markdown is returned unchanged. Output schema: structuredContent.result contains the response string: serialized JSON or unchanged Markdown. The same string is included in text content. Tool failures preserve this wrapper and set isError to true. Guided search: Searches can request missing engine parameters from supporting clients using the engine catalog and engine-specific rules. Flights collect airports and dates, hotels collect the destination and stay dates, and directions collect missing endpoints. Other clie
modeparams100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
{ "mcpServers": { "serpapi": { "type": "http", "url": "https://mcp.serpapi.com/YOUR_SERPAPI_API_KEY/mcp" } }}openclaw mcp add serpapi --url https://mcp.serpapi.com/YOUR_SERPAPI_API_KEY/mcp --transport streamable-httpclaude mcp add --transport http serpapi https://mcp.serpapi.com/mcp --header "Authorization: Bearer YOUR_SERPAPI_API_KEY"hermes mcp add serpapi --url https://mcp.serpapi.com/YOUR_SERPAPI_API_KEY/mcpcodex mcp add serpapi --url https://mcp.serpapi.com/mcp --bearer-token-env-var SERPAPI_API_KEYgit clone https://github.com/serpapi/serpapi-mcp.gitcd serpapi-mcpuv sync && uv run src/server.py{ "mcpServers": { "serpapi": { "type": "http", "url": "http://localhost:8000/YOUR_SERPAPI_API_KEY/mcp" } }}{ "mcpServers": { "serpapi": { "command": "uv", "args": ["run", "--directory", "/path/to/serpapi-mcp", "--frozen", "--no-dev", "src/stdio.py"], "env": { "SERPAPI_API_KEY": "YOUR_SERPAPI_API_KEY" } } }}# Header-basedcurl "https://mcp.serpapi.com/mcp" -H "Authorization: Bearer your_key" -d '...'
# Path-basedcurl "https://mcp.serpapi.com/your_key/mcp" -d '...'{"name": "search", "arguments": {"params": {"q": "coffee shops", "location": "Austin, TX"}}}{"name": "search", "arguments": {"params": {"q": "weather in London"}}}{"name": "search", "arguments": {"params": {"q": "AAPL stock"}}}{"name": "search", "arguments": {"params": {"q": "news"}, "mode": "compact"}}{"name": "search", "arguments": {"params": {"q": "detailed search"}, "mode": "complete"}}{"name": "search", "arguments": {"params": {"q": "news", "output": "md"}}}{"name": "search", "arguments": {"params": {"engine": "amazon", "k": "mechanical keyboards", "amazon_domain": "amazon.com", "output": "md"}}}{"name": "search", "arguments": {"params": {"engine": "google_scholar", "q": "retrieval augmented generation"}}}{"name": "search", "arguments": {"params": {"engine": "youtube", "search_query": "how to make espresso"}}}{"name": "search", "arguments": {"params": {"engine": "apple_app_store", "term": "habit tracker"}}}{"name": "search", "arguments": {"params": {"engine": "ebay", "_nkw": "vintage mechanical keyboard"}}}{"name": "extract", "arguments": {"params": {"url": "https://example.com"}}}{"name": "extract", "arguments": {"params": {"url": "https://example.com"}, "mode": "compact"}}{"name": "extract", "arguments": {"params": {"url": "https://example.com", "output": "md"}}}{"name": "extract", "arguments": {"params": {"url": "https://example.com", "mode": "map"}}}{"name": "extract", "arguments": {"params": {"url": "https://example.com", "mode": "crawl", "max_pages": 2}}}