MCP Retrieval
Local Go MCP server: DuckDuckGo/Bing web + image search, readability scraping to Markdown.
MCP-Server · von Role1776
Überblick
MCP Retrieval ist ein MCP-Server von Role1776. Marktplätze, die wir lesen und die es listen: 1 (Official MCP Registry). Wir haben es erstmals am 2026-10-11 gesehen und seither keine Änderung erfasst. Stand unseres Marktplatz-Durchlaufs vom 2026-10-12.
Was es abfragt
- Läuft auf Ihrem Rechner
- Geheimnisse: 2
- Einstellungen: 23
Erfordert: PROXY_LOGIN (geheim), PROXY_PASSWORD (geheim)
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als lokaler MCP-Server: Docker-Image
Erstellt aus den Angaben von Official MCP Registry.
claude mcp add --env "PROXY_LOGIN=<YOUR_PROXY_LOGIN>" --env "PROXY_PASSWORD=<YOUR_PROXY_PASSWORD>" --transport stdio mcp-retrieval -- docker run -i --rm -e PROXY_LOGIN -e PROXY_PASSWORD ghcr.io/role1776/mcp-retrieval:0.1.9[mcp_servers.mcp-retrieval]
command = "docker"
args = ["run", "-i", "--rm", "-e", "PROXY_LOGIN", "-e", "PROXY_PASSWORD", "ghcr.io/role1776/mcp-retrieval:0.1.9"]
[mcp_servers.mcp-retrieval.env]
PROXY_LOGIN = "<YOUR_PROXY_LOGIN>"
PROXY_PASSWORD = "<YOUR_PROXY_PASSWORD>"{
"mcpServers": {
"mcp-retrieval": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PROXY_LOGIN",
"-e",
"PROXY_PASSWORD",
"ghcr.io/role1776/mcp-retrieval:0.1.9"
],
"env": {
"PROXY_LOGIN": "<YOUR_PROXY_LOGIN>",
"PROXY_PASSWORD": "<YOUR_PROXY_PASSWORD>"
}
}
}
}docker run -i --rm -e "PROXY_LOGIN=<YOUR_PROXY_LOGIN>" -e "PROXY_PASSWORD=<YOUR_PROXY_PASSWORD>" ghcr.io/role1776/mcp-retrieval:0.1.9Ersetzen Sie die Werte in spitzen Klammern durch Ihre eigenen. Wir zeigen die Namen der Einstellungen, nie Werte.
Weitere optionale Einstellungen laut Marktplatz: DEFAULT_DOCUMENT_CHARS, DEFAULT_IMAGES, DEFAULT_RESULTS, DEFAULT_TIMEOUT_MS, LOG_MODE, MAX_DOCUMENT_CHARS, MAX_IDLE_CONNS_PER_HOST, MAX_IMAGES, MAX_QUERIES, MAX_RESULTS, MAX_TIMEOUT_MS, MCP_NAME, MCP_PATH, MCP_TRANSPORT, MIN_TIMEOUT_MS, PROXY_HOST, PROXY_PORT, PROXY_SCHEME, SERVER_PORT, SERVER_READ_TIMEOUT, SERVER_WRITE_TIMEOUT.
Startargumente speichern wir nicht. Braucht der Server welche, nennt sie seine eigene Dokumentation.
Wo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Official MCP Registry (Eintrag in der Registry öffnen) | Gelistet | 0.1.9 | Forks (GitHub): 0 Sterne (GitHub): 15 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
Was sich geändert hat
Bei diesem Plugin hat sich nichts bewegt, seit wir es beobachten.
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.
-
web-search ai.keenable/web-search
Live web search and clean-markdown page fetch over the Keenable web index.
-
No-API-key web search, page fetching and document reading across many engines. Local-first.
-
Search the web, news, images, videos and books, and extract page content for AI agents.
-
Zero-API-key MCP search server: multi-engine web/academic search, PDF parsing, secure web fetch
-
Web search, AI agent, and content extraction via You.com APIs
-
Secure MCP server for public web search and URL fetching.
-
search com.neurobird/search
Web search for AI agents. Ranked results with page passages already extracted, plus URL to markdown.
-
Web search and page extraction across several independent search providers.
-
Provider-neutral web_search for AI agents. Grounding + agent search APIs, keyless defaults.
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
gsearch io.github.daanielcruz/gsearch
Free Google Search with inline citations for any MCP-compatible AI tool.
-
Web search and content fetching with privacy-aware tool selection. Turns vague questions into optimized multi-engine queries, evaluates result quality, and re-searches when…
-
Search, scrape, and crawl the web for AI agents. Batch scraping and answers with citations.
-
The complete web toolkit for your agent. Search the web and get answers in milliseconds. Fetch any URL and get clean markdown content back. Send a browser agent to navigate sites…
-
You.com agent skills for web search, research with citations, and content extraction. Guided integrations for Vercel AI SDK, Claude Agent SDK, OpenAI Agents SDK, crewAI…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers…
-
You.com agent skills for web search, research with citations, and content extraction. Guided integrations for Vercel AI SDK, Claude Agent SDK, OpenAI Agents SDK, crewAI…
-
Build AI applications with real-time web data using Tavily's search, extract, crawl, and research APIs.
-
Web scraping and crawling powered by Firecrawl. Turn any website into clean, LLM-ready markdown or structured data. Scrape single pages, crawl entire sites, search the web, and…
-
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot…
Gelistet auf Claude: knowledge-work-plugins (5)
-
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers…
-
The complete web toolkit for your agent. Search the web and get answers in milliseconds. Fetch any URL and get clean markdown content back. Send a browser agent to navigate sites…
-
Build AI applications with real-time web data using Tavily's search, extract, crawl, and research APIs.
-
Search across all of your company's tools in one place. Find anything across email, chat, documents, and wikis without switching between apps.
-
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot…
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
The Dropbox plugin for ChatGPT connects your Dropbox files directly to ChatGPT. You can access files, save ChatGPT-generated content to Dropbox, and create sharing links without…
-
Use Google Drive as the single entrypoint for Drive, Docs, Sheets, and Slides work.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Work with Zotero from Codex: search your library, export BibTeX, insert citations, and import references through the Zotero desktop app.
-
General life-sciences research workflows with query routing, evidence synthesis, and optional parallel subagent analysis across genetics, omics, biology, chemistry, structure…
Gelistet auf Community GitHub marketplaces (5)
-
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers…
-
Web scraping and crawling powered by Firecrawl. Turn any website into clean, LLM-ready markdown or structured data. Scrape single pages, crawl entire sites, search the web, and…
-
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot…
-
One MCP, many parsers. Routes between markitdown, Docling, and LlamaParse. Plus an interpret tool…
-
FastMCP server for Obsidian wikilink suggestions from a pre-computed knowledge g
FastMCP server for Obsidian wikilink suggestions from a pre-computed knowledge graph (graphify…
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
Three-layer verification pipeline for AI output. Extracts claims, finds sources, and flags hallucination risks so humans can verify before acting.
-
Helps devs extract data from any website with thousands of trusted scrapers, crawlers, and automations from Apify Store. Integrate ready-made Actors to access all popular social…
-
Access official Microsoft documentation, API references, and code samples for Azure, .NET, Windows, and more.
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
-
Opens a real Chromium window you can navigate and interact with from a Copilot canvas control panel and agent actions.
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
Gelistet auf Cursor: cursor/plugins (5)
-
Browse and automate the web with TinyFish: run multi-step web automations, search the web, extract clean page content, and drive remote stealth browser sessions.
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
Generate presentations, documents, and webpages.
-
Search media and social mentions and pull analytics.
-
Browse, search, and read Microsoft OneDrive files.
Gelistet auf Docker MCP Catalog (5)
-
tavily-mcp io.github.tavily-ai/tavily-mcp
MCP server for advanced web search using Tavily
-
Exa AI web search, deep research, and content extraction. Provides MCP tools and research skills for comprehensive web search, people discovery, company research, academic papers…
-
Community-maintained server for DuckDuckGo search. Not published by or affiliated with DuckDuckGo.
-
brave-search-mcp-server io.github.brave/brave-search-mcp-server
Brave Search MCP Server: web results, images, videos, rich results, AI summaries, and more.
-
Connector for Perplexity API, to enable real-time, web-wide research.
Gelistet auf Official MCP Registry (5)
-
Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.
-
web-search ai.keenable/web-search
Live web search and clean-markdown page fetch over the Keenable web index.
-
No-API-key web search, page fetching and document reading across many engines. Local-first.
-
Search the web, news, images, videos and books, and extract page content for AI agents.
-
Zero-API-key MCP search server: multi-engine web/academic search, PDF parsing, secure web fetch
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Ist das Ihr Plugin?
Fügen Sie es Ihren Projekten hinzu und belegen Sie, dass Sie es pflegen: mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag. Sie erhalten Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Official MCP Registry. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.