MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
th2-reportupdated this year
MCP server for TH2 Report Viewer — search test events, drill into results, find failures
npm -
mcp_tools_3github.com/xiaobenyang-com/mcp_tools_3no update data
Find files by glob pattern and search within them using grep. Quickly locate filenames and content matches across your workspace. Focus searches to a chosen directory for precise results.
smithery -
readfile_mcpgithub.com/xue20010808/readfile_mcpno update data
Explore your local files with fast glob matching and text search. Find files across directories and pinpoint patterns in code, logs, or docs. Focus searches on any folder to keep results relevant.
smithery -
Find tools beyond the usual search results. Local-first MCP index of FMHY, Awesome Lists & userscripts. | 资源雷达
★ 1 -
Free plugins for Claude Code and Codex: Google indexing, Search Console, site audits, live Google results, and a resume kit tailored to one job. From Find Untapped Growth.
mcpb MIT -
SkillMap-AI-Agent-MCPgithub.com/Ebbeju-Lankapalli/SkillMap-AI-Agent-MCPupdated this year
SkillMap is an AI career assistant that helps students explore demand for a skill and find related jobs in India. It uses MCP tools for web research and JSearch for job listings, then remembers the results so users can ask about a specific opening.
NOASSERTION ★ 1 -
Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
npm MIT -
Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
npm MIT -
MCP server for Person LinkedIn URL Resolver. Find a person's LinkedIn profile URL from their name and company, with a match confidence and a current or former employer flag, read from Google result pages. Never opens LinkedIn. Runs on Apify. Clay-ready output.
npm MIT -
Brave Searchno update data
Enable comprehensive web search capabilities including web, image, news, video, and local points of interest searches using Brave's API. Enhance your applications with rich, up-to-date search results tailored to your queries. Access diverse search results as resources for seamless integration.
smithery -
pandas-doctorgithub.com/furqan-khan07/pandas-doctorno update data
Finds slow pandas code, checks rewrites give identical results on your data, measures speedups.
pypi -
TypeScript MCP server that accepts natural-language queries from a React (Vite) client (e.g. “Where can I find my resume documents?”), sends the query to the Gemini agent, uses the agent’s plan to call safe filesystem tools (list_files, read_file, search_files, get_file_info), and returns results to the client.
MIT -
The Brave Search API as a CLI and local MCP server — ranked web results, page text pre-extracted to a token budget for grounding a model, and cited answers from one search or a multi-step research run. Every result prints its cost; nothing is cached (Brave ToS)
MIT -
DuckDuckGo search results as JSON: ranked results with ads in their own array, 37 regions.
npm MIT -
An MCP server enhances AI responses with real-time search results via Higress ai-search.
Apache-2.0 ★ 5 -
YouTube Extended Search — FlashDatano update data
# YouTube Extended Search — FlashData Search larger YouTube video result sets, with up to 700 requested results. Map recurring channels and topics from structured video records. Group a larger topic sample by channelId or channelUrl to see which creators appear repeatedly, retaining the underlying video IDs. [YouTube Extended Search API documentation and examples](https://flashdata.dev/docs/sources/youtube_search_extended?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_search_extended-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Extended Search listing](https://smithery.ai/servers/flashdata/youtube-extended-search) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_search_extended`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_search_extended` without submitting a data query. After approving your data-call budget, try: > Search for 100 battery recycling videos, group the observed results by channel, and retain video IDs for later review. This server exposes `youtube_search_extended`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call max_results accepts 1–700, default 20. This is the extended-search product with its own higher rate, not repeated standard search or a guarantee of 700 returned records. The same supported filters are available. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_search_extended", "arguments": { "query": "battery recycling", "max_results": 100 } } ``` ## Work with the output Read results[0].results and group by channelId or channelUrl. Keep the original video IDs and count observed results per channel; retain channel labels for review. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_search_extended", "status": "done", "results": [ { "results": [ { "videoId": "dQw4w9WgXcQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 }, { "videoId": "aqz-KE-bpKQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The request limit is 700, not a promise of 700 returned videos or pagination. Extended search has its own rate, higher than standard search. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
web-searchgithub.com/cardea-mcp/web-searchupdated this year
A Model Context Protocol (MCP) server provides web search capabilities leveraging the Tavily API to fetch and return web search results.
★ 1 -
@om-surushe/efficient-searchgithub.com/om-surushe/efficient-searchupdated this year
MCP server for compact Google Programmable Search results
npm MIT -
adaptive-transformer-search-mcpgithub.com/Particular-Audience/adaptive-transformer-search-mcpstale
MCP Server for Adaptive Transformer Search - AI-powered eCommerce product search using LLM semantic understanding to eliminate zero search results.
MIT ★ 5 -
mcp_searchagentgithub.com/Thiruvel-AP/mcp_searchagentupdated this year
Search agent using the Model Context Protocol (MCP) to let an LLM (GPT-OSS-20B) based agent query external search providers and return structured results. Store the result in the postgreSQL integrated with the exograph.
-
A Model Context Protocol (MCP) server that provides a tool for performing Google searches and retrieving the content of the top results.
★ 5 -
EfficientSearchgithub.com/om-surushe/EfficientSearchupdated this year
MCP server for compact Google Programmable Search results.
MIT -
agadmator-searchgithub.com/josephwilliams/agadmator-searchupdated this year
Search agadmator’s chess video archive by player, opening, result, tactics, move count, time control, and natural
MIT -
@tetradice/mcp-server-searchupdated this year
Query the MCP Registry, Smithery, and GitHub in parallel and return normalized search results.
npm MIT -
search-aggregate-mcpgithub.com/florianherrengt/search-aggregate-mcpupdated this year
MCP server that fires multiple search engines in parallel and merges results by frequency
npm MIT -
ddgsgithub.com/deedy5/ddgsactive
Dux Distributed Global Search. A metasearch library that aggregates results from diverse web search services.
pypi MIT -
Find the best GTM APIs. We benchmark all the GTM APIs and we put the results on our website.
MIT ★ 2 -
Airbnb Search Serverno update data
Search for Airbnb listings and get detailed information about accommodations. Access direct links to Airbnb listings in your search results, making it easy to plan your next trip.
smithery -
MCP server with web search tool using Ollama's API. Enables AI assistants to search internet via standardized protocol. Ruby implementation with error handling and result formatting.
MIT ★ 1 -
paper-search-servergithub.com/ganlin770/paper-search-serverupdated this year
MCP server for academic paper search via Elsevier Scopus API — Flask-based, caching, structured results for LLM research workflows
-
gai-mcp-googlergithub.com/kakkoii1337/gai-mcp-googlerupdated this year
MCP Server for scraping Google search results
npm MIT -
mcp-web-searchgithub.com/DmitriyOT/mcp-web-searchupdated this year
MCP server for LLM-optimized web search: DuckDuckGo/Serper/Bing, result aggregation, stealth scraping, OCR, caching & rate limiting
MIT -
Keyless web search for AI agents through your own SearXNG instance. One MCP tool, zero API keys, zero tracking. Engine-transparent results.
Apache-2.0 -
@quarryserp/mcpactive
Official Quarry MCP server for Google search results in AI agents.
npm MIT -
Assertline's hosted MCP server: find your recorded web tests, run them and read step-by-step results. Instructions only.
MIT -
A MCP server implementation for SearXNG, designed to enhance search result processing and context-aware querying.
Apache-2.0 -
serpens-mcpactive
MCP server for SERPens — Google Search & SERP API. Structured or Markdown search results for AI agents.
npm MIT -
A smart MCP server for multi-engine web search with AI-powered results
pypi Apache-2.0 -
DuckDuckGo Search API on Apify - Python (uv) + MCP example. DuckDuckGo search results as clean, structured JSON.
★ 3 -
mcp-web-rag-searchgithub.com/IshaanLabs/mcp-web-rag-searchupdated this year
Model Context Protocol (MCP) powered Web Search + Retrieval Augmented Generation system that scrapes web results and uses vector similarity search to generate accurate AI answers.
MIT -
Standalone MCP web search powered by OpenCode free models, with verified source URLs and structured JSON results.
★ 3 -
web-search-mcpgithub.com/pranavms13/web-search-mcpupdated this year
A Model Context Protocol (MCP) server that provides web search functionality using a headless Chrome browser to scrape Google, DuckDuckGo and Bing search results.
MIT ★ 16 -
This is a Model Context Protocol (MCP) server that provides Google search functionality with intelligent result summarization. It's designed to integrate seamlessly with AI assistants like Cline to enable web search capabilities.
MIT -
llm-context-searchgithub.com/rorlikowski/llm-context-searchupdated this year
llm-context-search is a fast, LLM-free engine that turns web search results into clean, ranked, token-bounded context for AI agents.
pypi MIT -
🔍 Search and cache PyPI packages using regex for fast, detailed results on names, versions, maintainers, and descriptions.
-
Stream Brave Search (web & local) results via a Model Context Protocol (MCP) / Server-Sent Events (SSE) interface. Acts as a centralized, observable tool provider for AI models, deployable via Docker or Helm.
MIT ★ 16 -
MCP server exposing QA-lifecycle agents over a traceability spine: requirement -> findings -> tests -> results -> release verdict, with provenance for every AI-produced artifact.
npm MIT -
Full-text search across 49M Hacker News stories and comments, powered by Postgres with BM25 ranking for instant results.
-
One stdio MCP server that combines DeepSeek and Exa web search into a single deduplicated result set. Configure both API keys or just one.
MIT -
sift-mcpgithub.com/enmito/sift-mcpupdated this year
MCP server that wraps Brave Search and augments each result with a transparent quality vector for AI agents.
MIT -
MCP server for real-time Google search and Google Maps results (serpgrab, SerpApi-compatible)
npm MIT -
Baidu Search API (百度搜索 API) on Apify - Python (uv) + MCP example. Baidu search results as clean, structured JSON. 百度搜索结果,干净的结构化 JSON 数据。
MIT -
serp-itgithub.com/luka-dev/serp-itupdated this year
MCP Tool, that can utilize multiple search engines and processing to provide AI ready results
npm ★ 3 -
A lightweight, pure web search solution for large language models, supporting multi-engine aggregated search, deep reflection and result evaluation. A balanced approach between web search and deep research, providing a framework-free implementation and mcp server for easy developer integration.
Apache-2.0 ★ 2 -
An MCP server for (free!) search results via duckduckgo
★ 1 -
Groundlinkgithub.com/ohhavefun/groundlinkno update data
Cited web search for MCP hosts. Returns source-bearing results from Groundlink.
npm -
grok2api-mcp-servergithub.com/wousp112/grok2api-mcp-serverupdated this year
MCP server for real-time web search via Grok — structured results with sources, confidence scores, and multi-language support
MIT ★ 4 -
Local-first knowledge retrieval for AI agents, combining FTS5, vector search, reranking, and traceable MCP results.
MIT -
Serpex MCP server: web search API and extract API for AI agents. Ranked web results, optionally with page content as markdown, and page extraction
npm MIT -
visual-image-search-mcpgithub.com/enescanguven/visual-image-search-mcpupdated this year
MCP server that searches the web for images, composites the results into a numbered contact sheet the model can actually look at, and downloads the ones it picks. Zero-config, no API key required.
npm MIT