SerpApi와 통합하여 포괄적인 검색 엔진 결과 및 데이터 추출을 제공하는 MCP(Model Context Protocol) 서버 구현입니다.
멀티 엔진 검색: Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay 및 기타
엔진 리소스: MCP 리소스를 통해 엔진별 매개변수 스키마 제공 (검색 도구 참조)
실시간 날씨 데이터: 검색 쿼리를 통한 위치 기반 날씨 및 예보
주식 시장 데이터: 검색 통합을 통한 기업 재무 및 시장 데이터
동적 결과 처리: 다양한 결과 유형을 자동으로 감지하고 형식 지정
유연한 응답 모드: 전체 또는 간결한 JSON 응답
JSON 응답: 전체 또는 간결한 모드를 갖춘 구조화된 JSON 출력
Related MCP server: SearXNG MCP Server
SerpApi MCP 서버는 mcp.serpapi.com에서 호스팅 서비스로 제공됩니다. 연결하려면 API 키를 제공해야 합니다. API 키는 SerpApi 대시보드에서 찾을 수 있습니다.
Claude Desktop이 호스팅된 서버를 사용하도록 구성할 수 있습니다:
{
"mcpServers": {
"serpapi": {
"type": "http",
"url": "https://mcp.serpapi.com/YOUR_SERPAPI_API_KEY/mcp"
}
}
}git clone https://github.com/serpapi/serpapi-mcp.git
cd serpapi-mcp
uv sync && uv run src/server.pyClaude Desktop 구성:
{
"mcpServers": {
"serpapi": {
"type": "http",
"url": "http://localhost:8000/YOUR_SERPAPI_API_KEY/mcp"
}
}
}API 키 가져오기: serpapi.com/manage-api-key
두 가지 방법이 지원됩니다:
경로 기반: /YOUR_API_KEY/mcp (권장)
헤더 기반: Authorization: Bearer YOUR_API_KEY
예시:
# Path-based
curl "https://mcp.serpapi.com/your_key/mcp" -d '...'
# Header-based
curl "https://mcp.serpapi.com/mcp" -H "Authorization: Bearer your_key" -d '...'MCP 서버에는 모든 SerpApi 엔진과 결과 유형을 지원하는 하나의 주요 검색 도구가 있습니다. 사용 가능한 모든 매개변수는 SerpApi API 참조에서 확인할 수 있습니다.
엔진 매개변수 스키마는 serpapi://engines (인덱스) 및 serpapi://engines/<engine>와 같은 MCP 리소스로도 노출됩니다.
제공할 수 있는 매개변수는 각 API 엔진마다 다릅니다. 아래에 몇 가지 샘플 매개변수가 있습니다:
params.q (필수): 검색 쿼리
params.engine: 검색 엔진 (기본값: "google_light")
params.location: 지리적 필터
mode: 응답 모드 - "complete" (기본값) 또는 "compact"
...SerpApi API 참조에서 다른 매개변수 확인
예시:
{"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"}}지원되는 엔진: Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay 등 (serpapi://engines 참조).
결과 유형: 답변 상자, 유기적 결과, 뉴스, 이미지, 쇼핑 - 자동으로 감지되고 형식이 지정됩니다.
# Local development
uv sync && uv run src/server.py
# Docker
docker build -t serpapi-mcp . && docker run -p 8000:8000 serpapi-mcp
# Regenerate engine resources (Playground scrape)
python build-engines.py
# Testing with MCP Inspector
npx @modelcontextprotocol/inspector
# Configure: URL mcp.serpapi.com/YOUR_KEY/mcp, Transport "Streamable HTTP transport""Missing API key": URL 경로 /{YOUR_KEY}/mcp 또는 헤더 Bearer YOUR_KEY에 키를 포함하세요.
"Invalid key": serpapi.com/dashboard에서 확인하세요.
"Rate limit exceeded": 잠시 기다리거나 SerpApi 플랜을 업그레이드하세요.
"No results": 다른 쿼리나 엔진을 시도해 보세요.
저장소를 포크하세요.
기능 브랜치를 만드세요: git checkout -b feature/amazing-feature
종속성을 설치하세요: uv install
변경 사항을 적용하세요.
변경 사항을 커밋하세요: git commit -m 'Add amazing feature'
브랜치에 푸시하세요: git push origin feature/amazing-feature
Pull Request를 여세요.
MIT 라이선스 - 자세한 내용은 LICENSE 파일을 참조하세요.
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 clients receive a missing-parameter error. Cancellation does not run a search.
Examples:
Weather: {"params": {"q": "weather in London", "engine": "google"}, "mode": "complete"}
Stock: {"params": {"q": "AAPL stock", "engine": "google"}, "mode": "complete"}
General: {"params": {"q": "coffee shops", "engine": "google_light", "location": "Austin, TX"}, "mode": "complete"}
Compact: {"params": {"q": "news"}, "mode": "compact"}
Markdown: {"params": {"q": "news", "output": "md"}}
Supported engines include (not limited to):
- google
- google_light
- google_flights
- google_hotels
- google_images
- google_news
- google_local
- google_shopping
- google_jobs
- bing
- yahoo
- duckduckgo
- youtube_search
- baidu
- ebay
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Response mode (default: "complete") - "complete": Returns the full response - "compact": Removes metadata fields from JSON responses; Markdown is unchanged | complete |
| params | No | Dictionary of SerpApi engine-specific parameters. Common parameters include: - q: Search query (required for most engines) - engine: Search engine to use (default: "google_light") - location: Geographic location filter - output: Response format; omit for JSON or set to "md" for Markdown |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavioral context beyond that: compact versus complete response modes, Markdown behavior, output wrapper structure, guided-search interaction for missing parameters, cancellation semantics, and failure wrapper behavior. This goes well beyond what annotations or schema alone provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-organized with clear sections, bullet lists, and examples. The engine-discovery instructions are repeated twice, which is mildly redundant, but the overall structure is scannable and every major section earns its place given the tool's breadth.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a broad, engine-flexible tool, the description is remarkably complete: it covers when to use the tool, how to discover supported engines, parameter conventions, response modes, output schema, guided-search behavior, and realistic examples. With a rich output schema and annotations present, no critical operational detail is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds meaningful guidance beyond the schema: it explains which parameters are common, notes 'q' is required for most engines, gives concrete JSON examples, and points to MCP resources for engine-specific parameter discovery. This helps an agent construct valid params far better than the raw schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: a universal search tool covering 'all SerpApi engines and result types.' It clearly enumerates the kinds of live structured SERP data it retrieves. However, it never explicitly contrasts itself with the sibling tools search_dashboard and search_table, so the differentiation is implicit rather than stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'When to use' section explicitly lists concrete scenarios such as web results, news, product listings, flights, and videos, giving an agent clear selection criteria. It does not mention when not to use the tool or point to sibling alternatives, but the listed conditions are specific enough to guide invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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).
| Name | Required | Description | Default |
|---|---|---|---|
| params | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, non-destructive, and open-world hints. The description adds behavior beyond these: it describes the interactive rendering in conversation and the automatic selection of engine-specific dashboards (e.g., google_flights), which is valuable context. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences with zero fluff. The key differentiator (dashboard variant) is front-loaded, followed by output details and usage guidance. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a variant tool, the description is complete: it states what it returns, when to use it, and where to get parameter details. It does not mention pagination or error handling, but these are not critical for a read-only dashboard tool with annotations already covering safety.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has one opaque `params` object with 0% coverage. The description compensates by stating 'Same params as `search`', directing the agent to the sibling's schema for parameter details. This is a pragmatic and effective way to convey parameter meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it is an interactive dashboard variant of `search`, enumerating the specific outputs (summary metrics, source breakdown chart, results table with expandable detail panel). This distinguishes it from the sibling tools `search` and `search_table` without ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It says 'Use for a richer visual overview of a query's results', giving clear context for when to select this tool. It also notes 'Same params as `search`', implying the simpler `search` tool may be used for non-visual needs, though it does not explicitly name alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| params | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and destructiveHint, covering the safety profile. The description adds useful behavioral context beyond that: results are organic, the table is sortable/searchable, it renders in the conversation, and it depends on MCP Apps support. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no filler. The first sentence front-loads the core purpose and sibling relationship; the second gives the usage condition. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a thin wrapper around `search`, the description covers purpose, differentiation, when to use it, and the parameter relationship. Annotations cover read-only safety, and there is no output schema to document. It only lacks explicit handling of what happens when the host lacks MCP Apps support, and its parameter semantics depend on the parent tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has a single opaque `params` object with additionalProperties true and 0% description coverage, so the description must compensate. Saying 'Same params as `search`' adds meaning by reference and tells the agent to reuse another tool's parameter definitions, but it does not enumerate or describe those parameters, leaving the payload underspecified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's behavior: it returns organic results as an interactive, sortable/searchable table rendered in the conversation. It explicitly positions itself as a 'variant of `search`', which distinguishes it from the sibling tool without needing to open any schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives a concrete use condition: 'Use when the host supports MCP Apps and the user wants to browse results visually rather than read JSON.' It points to the alternative `search`, but does not explicitly state when not to use this tool or address the `search_dashboard` sibling, so it stops short of fully explicit routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v2.0.0search3 fields changedInput schema / properties / params / additionalPropertiesRemoved value: -trueInput schema / properties / params / anyOfAdded value: +[
+ {
+ "additionalProperties": true,
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / params / typeRemoved value: -"object"v1.0.3searchsearch_dashboardsearch_tableScored across 3 tools
The three tools are clearly labeled as base search, dashboard, and table variants, with descriptions explaining when to use each. However, they all wrap the same underlying SerpApi search, so semantic overlap is inherent and an agent must rely on the presentation-focused descriptions to select correctly.
All tool names follow a consistent pattern: the base 'search' plus descriptive 'search_dashboard' and 'search_table' variants. There is no mixing of naming conventions or styles.
Three tools is minimal but appropriate for a search API wrapper: one universal search operation and two UI presentation variants. The count is lean but not deficient.
The search tool covers all SerpApi engines and output modes, so the core domain is fully covered with no dead ends. Minor gaps like explicit pagination or account-related operations are not exposed, but they are not essential to the server's purpose.
Official SerpApi MCP server for Google, Bing, and other search engines.
MCP server for Google search results via SERP API
Serper MCP — wraps the Serper Google Search API (serper.dev)
SerpApi MCP — wraps SerpApi (serpapi.com) search engines