Unified Search MCP Server

1. 저장소 클론: ```bash git clone https://github.com/JDeun/unified-search-mcp-server.git cd unified-search-mcp-server ```

Local serverstdioPython

What is the Unified Search MCP server?

Unified Search MCP server exists for a simple reason — assistants are far more useful when they can act on Unified Search directly instead of describing what you should do. 1. 저장소 클론: bash git clone https://github.com/JDeun/unified-search-mcp-server.git cd unified-search-mcp-server .

What the assistant can call

Once Unified Search is connected, these are the calls the assistant has available:

  • unified_search — 모든 소스에서 동시에 검색합니다. python results = await unified_search( query="인공지능", sources=["scholar", "web", "youtube"], num_results=10 )
  • search_google_scholar — 학술 논문을 검색합니다. python results = await search_google_scholar( query="머신러닝", author="Yann LeCun", year_start=2020, year_end=2024, num_results=10 )
  • search_google_web — 웹을 검색합니다. python results = await search_google_web( query="ChatGPT", language="ko", safe_search="medium", num_results=10 )
  • search_youtube — YouTube 동영상을 검색합니다. python results = await search_youtube( query="파이썬 튜토리얼", video_duration="medium", upload_date="month", order="viewCount"
  • get_author_info — Google Scholar에서 저자 정보를 가져옵니다. python info = await get_author_info("Geoffrey Hinton")
  • clear_cache — 캐시된 검색 결과를 삭제합니다. python await clear_cache(source="web") # 또는 None으로 전체 삭제
  • get_api_usage_stats — API 사용량과 제한을 모니터링합니다. python stats = await get_api_usage_stats()

Configuration and credentials

You will need 6 environment variables: GOOGLE_API_KEY, GOOGLE_CUSTOM_SEARCH_ENGINE_ID, YOUTUBE_API_KEY, MCP_ENCRYPTION_KEY, MCP_RATE_LIMIT_SECRET, MCP_REDIS_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Unified Search's toolset — unified_search, search_google_scholar, search_google_web and 4 more — is a fair guide to whether it matches your workflow. It is maintained by JDeun; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the unified search mcp server does with a few real requests.

Available tools

ToolWhat it does
unified_search모든 소스에서 동시에 검색합니다. python results = await unified_search( query="인공지능", sources=["scholar", "web", "youtube"], num_results=10 )
search_google_scholar학술 논문을 검색합니다. python results = await search_google_scholar( query="머신러닝", author="Yann LeCun", year_start=2020, year_end=2024, num_results=10 )
search_google_web웹을 검색합니다. python results = await search_google_web( query="ChatGPT", language="ko", safe_search="medium", num_results=10 )
search_youtubeYouTube 동영상을 검색합니다. python results = await search_youtube( query="파이썬 튜토리얼", video_duration="medium", upload_date="month", order="viewCount", num_results=20 )
get_author_infoGoogle Scholar에서 저자 정보를 가져옵니다. python info = await get_author_info("Geoffrey Hinton")
clear_cache캐시된 검색 결과를 삭제합니다. python await clear_cache(source="web") # 또는 None으로 전체 삭제
get_api_usage_statsAPI 사용량과 제한을 모니터링합니다. python stats = await get_api_usage_stats()

How to install the Unified Search MCP server

{
  "mcpServers": {
    "unified-search": {
      "command": "python",
      "args": ["/path/to/unified_search_server.py"],
      "env": {
        "GOOGLE_API_KEY": "your-key",
        "GOOGLE_CUSTOM_SEARCH_ENGINE_ID": "your-cse",
        "YOUTUBE_API_KEY": "your-key"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
GOOGLE_API_KEYCredential the server authenticates with.Yes
GOOGLE_CUSTOM_SEARCH_ENGINE_IDConfiguration value read at startup.Optional
YOUTUBE_API_KEYCredential the server authenticates with.Yes
MCP_ENCRYPTION_KEYCredential the server authenticates with.Yes
MCP_RATE_LIMIT_SECRETCredential the server authenticates with.Yes
MCP_REDIS_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Unified Search to unified search.
  • Use Unified Search to search google scholar.
  • Use Unified Search to search google web.

Frequently asked questions

It connects Unified Search to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (unified_search, search_google_scholar, search_google_web, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Unified Search directly.