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. 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.
-
基于 Playwright 的 Google 搜索 CLI 工具
npm ISC -
A tiny local MCP server (single ~1.8 MB binary, ~12 ms cold start) that gives any MCP client access to DeepSeek's Search and Fetch APIs. 把 DeepSeek 搜索/抓取接入任意 MCP 客户端。
MIT ★ 1 -
gh-find-code-mcpgithub.com/talwrii/gh-find-code-mcpupdated this year
An MCP server to find code on GitHub via gh search repos
pypi MIT License -
Local stdio MCP bridge between LM Studio Bionic and a Find Images.app MCP server. Provides next-level image search and information retrieval based on multimodal embeddings
MIT -
gh-find-code-mcpgithub.com/talwrii/gh-find-code-mcpupdated this year
—
★ 1 -
CarClever – Buying Assistant: MCP server for US new and used car search, VIN-linked NHTSA checks and side-by-side comparison, built on a daily Edmunds catalogue (via Impact).
MIT -
MCP server for scientific grounding: search arXiv, OpenAlex, Crossref, Semantic Scholar, PubMed — references/citations from paywalled journals via public metadata
MIT ★ 7 -
Find MCP - the npm client for the agentage MCP directory: thin stdio MCP proxy bridging stdio-only clients (Claude Desktop, Cursor, VS Code) to catalog.agentage.io/mcp - search 17,000+ MCP servers from any MCP client.
npm MIT -
MCP server for scientific grounding: search and discover open-source research papers and scholarly literature (arXiv, Semantic Scholar, OpenAlex, Crossref/Springer Nature, PubMed) — metadata, references and citations reachable even when the full text is paywalled.
pypi MIT -
Smart MCP tool to find and validate movie/tv-show resources with multiple sources support
npm MIT -
claude-code-conversation-search-mcpgithub.com/TonySimonovsky/claude-code-conversation-search-mcpstale
Stop losing Claude Code conversations. Search across all projects, find old chats, and resume where you left off.
MIT ★ 5 -
Code intelligence MCP server — let AI assistants explore your entire codebase, find callers, and trace impact in one query.
MIT ★ 1 -
Read-only MCP server + CLI to discover, rank, and vet on-chain stellar-8004 agents on Stellar mainnet — with an x402 (USDC) agent-finds-agent reference loop and on-chain reputation feedback
MIT ★ 1 -
Safely connect Google Search Console to Grok, Grok Bot and Cursor, so your agent can check rankings and clicks, find pages losing traffic, explain why a page isn't indexed and, on a paid plan, submit the sitemaps you approve.
MIT -
Flight and Stay Search Serverno update data
Provide comprehensive flight and accommodation search capabilities using the Duffel API. Search for one-way, round-trip, and multi-city flights, get detailed flight offer information, and find travel stays with guest reviews. Enable users to specify preferences such as cabin class, passenger count, and connection options for tailored travel planning.
smithery -
I couldn't find a good web grounding MCP server for Goose, so I made one for me. This server exposes a single "Agent" tool that combines real-time Google Search, deep URL analysis, and Python code execution to solve complex, multi-step research and data tasks.
MIT -
找客户 · Find Customers|销售线索与评论区获客no update data
找客户 · Find Customers|销售线索与评论区获客(OPC 评论线索雷达):从抖音、小红书和快手公开评论中识别高意向客户。官方用例:https://opc1.me/use-cases/comment-lead-generation ;与评论导出工具对比:https://opc1.me/compare/comment-lead-radar-vs-export-tools
smithery -
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 -
Multi search MCP server
MIT ★ 6 -
An open-source, local-first Model Context Protocol (MCP) server for **AI Search Crawler Governance, Brand Safety Guardrails, Canonical Integrity, and IndexNow Notifications
MIT -
mcp-brave-searchgithub.com/yuandeshoulian/mcp-brave-searchupdated this year
Brave Search MCP Server - Web and News Search via stdio
npm MIT -
n2-free-searchgithub.com/choihyunsus/n2-free-searchupdated this year
Free search MCP server powered by SearXNG — no API keys, no credit cards, just search. 70+ search engines.
npm MIT -
cowork-semantic-searchgithub.com/ZhuBit/cowork-semantic-searchupdated this year
—
AGPL-3.0 ★ 31 -
agent-search-mcpgithub.com/lennney/agent-search-mcpupdated this year
Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
npm Apache-2.0 -
—
MIT ★ 1 -
Retrieval platform for AI agents — 14 search providers, 12-step content extraction, dead URL recovery, site capture, and local corpus storage. One API.
pypi MIT -
MCP server for deep web search using @just-every/search
npm MIT -
MCP server for semantic code search and live web search, powered by Devin
npm MIT -
mcp-web-searchgithub.com/agentic-forge/mcp-web-searchupdated this year
Web Search MCP server using Brave Search API (FastMCP)
-
Runs a search across all major providers simultaneously
MIT ★ 9 -
Simple Google Search MCP
-
MCP server exposing Google Programmable Search Engine (PSE) tool.
Apache-2.0 -
Google Search Console integration for Model Context Protocol (MCP)
pypi MIT -
Local-first code and project-text retrieval, source-backed symbol analysis, caller-controlled web discovery, and MCP for SDK clients
npm MIT -
Model-independent Agent Skill and MCP server for DeepSeek official Search and Fetch APIs.
-
MiniMax Search is an MCP (Model Context Protocol) server that provides web search and browsing capabilities.
★ 64 -
agentic-searchgithub.com/cardea-mcp/agentic-searchupdated this year
A Model Context Protocol (MCP) server that provides agentic search capabilities with support for vector search using Qdrant, full-text search using TiDB, or both combined.
★ 10 -
Local MCP server for DeepSeek web search
npm MIT -
@caikiji/mcp-searchgithub.com/caikiji/mcp-searchupdated this year
MCP server for web search powered by SearXNG — privacy-respecting self-hosted metasearch
npm MIT -
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 -
Local-first search tool for Claude Code session transcripts — hybrid keyword + semantic search, with optional multi-source (federated) trust-tagged search.
pypi Apache-2.0 -
@dccxx/search-mcpstale
MCP server for searching information
npm MIT -
MCP Web Search Tool — Model Context Protocol server providing real-time web search, news, image search, and URL content extraction with pluggable providers (Brave, DuckDuckGo).
npm MIT -
raw-web-searchgithub.com/andresfortunato/raw-web-searchupdated this year
Open source MCP search server for Claude Code. Replaces WebSearch + WebFetch.
MIT ★ 1 -
Local MCP server for Kimi web search
npm MIT -
X search evidence for joint search with the host official Web Search
npm MIT -
MCP server that adds Google Custom Search web search to any MCP client.
★ 1 -
多后端联网搜索 MCP:专为 CC+DeepSeek 用户设计。支持 DuckDuckGo(免费)/Brave/Google/Bing,自动检测最优后端。
MIT ★ 1 -
google-search-console-mcpgithub.com/kn00m1/google-search-console-mcpupdated this year
MCP server for Google Search Console — search analytics, URL inspection, and sitemap management for AI assistants
MIT -
Read-only Google Search Console MCP for AI SEO analysis: search analytics, URL inspection, sitemaps.
MIT ★ 9 -
search_itgithub.com/quantumxiaol/search_itupdated this year
A MCP Server of Search and Crawler
MIT -
MCP Server for Sematic Searching
★ 7 -
在其他支持mcp的客户端中调用 ZCode 的 search_image mcp
MIT -
@dccxx/search-docs-mcp2stale
MCP server for searching documentation
npm MIT -
@dccxx/search-docs-mcpstale
MCP server for searching documentation
npm MIT -
Google Search Console MCP server: 20 read tools, no write tools.
npm Apache-2.0 -
MCP server exposing SearXNG web search and search suggestions
npm MIT -
MCP server for the Google Custom Search JSON API: web and image search via Programmable Search Engine with pagination, language and country filters and SafeSearch
MIT -
@getmcpads/google-search-console-mcp-servergithub.com/get-mcp-ads/google-search-console-mcp-serveractive
Google Search Console MCP server: 20 read tools, no write tools.
npm Apache-2.0 -
面向 AI Agent 的深度搜索 MCP 服务器。多引擎聚合搜索,内容质量过滤,正文抓取,跨轮去重,PDF 落盘与可引用归档。提供干净、可引用的研究材料。Deep Search MCP Server
MIT ★ 2