Argus Retrieval
Multi-provider search broker for AI agents: 14 providers, 12-step extraction, retrieval workflows.
MCP-Server · von Khamel83
Überblick
Argus Retrieval ist ein MCP-Server von Khamel83. 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: 6
- Einstellungen: 8
Erfordert: ARGUS_BRAVE_API_KEY (geheim), ARGUS_EXA_API_KEY (geheim), ARGUS_LINKUP_API_KEY (geheim), ARGUS_SERPER_API_KEY (geheim), ARGUS_TAVILY_API_KEY (geheim), ARGUS_WOLFRAM_API_KEY (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: PyPI-Paket
Erstellt aus den Angaben von Official MCP Registry.
claude mcp add --env "ARGUS_BRAVE_API_KEY=<YOUR_ARGUS_BRAVE_API_KEY>" --env "ARGUS_EXA_API_KEY=<YOUR_ARGUS_EXA_API_KEY>" --env "ARGUS_LINKUP_API_KEY=<YOUR_ARGUS_LINKUP_API_KEY>" --env "ARGUS_SERPER_API_KEY=<YOUR_ARGUS_SERPER_API_KEY>" --env "ARGUS_TAVILY_API_KEY=<YOUR_ARGUS_TAVILY_API_KEY>" --env "ARGUS_WOLFRAM_API_KEY=<YOUR_ARGUS_WOLFRAM_API_KEY>" --transport stdio argus -- uvx argus-search[mcp_servers.argus]
command = "uvx"
args = ["argus-search"]
[mcp_servers.argus.env]
ARGUS_BRAVE_API_KEY = "<YOUR_ARGUS_BRAVE_API_KEY>"
ARGUS_EXA_API_KEY = "<YOUR_ARGUS_EXA_API_KEY>"
ARGUS_LINKUP_API_KEY = "<YOUR_ARGUS_LINKUP_API_KEY>"
ARGUS_SERPER_API_KEY = "<YOUR_ARGUS_SERPER_API_KEY>"
ARGUS_TAVILY_API_KEY = "<YOUR_ARGUS_TAVILY_API_KEY>"
ARGUS_WOLFRAM_API_KEY = "<YOUR_ARGUS_WOLFRAM_API_KEY>"{
"mcpServers": {
"argus": {
"command": "uvx",
"args": [
"argus-search"
],
"env": {
"ARGUS_BRAVE_API_KEY": "<YOUR_ARGUS_BRAVE_API_KEY>",
"ARGUS_EXA_API_KEY": "<YOUR_ARGUS_EXA_API_KEY>",
"ARGUS_LINKUP_API_KEY": "<YOUR_ARGUS_LINKUP_API_KEY>",
"ARGUS_SERPER_API_KEY": "<YOUR_ARGUS_SERPER_API_KEY>",
"ARGUS_TAVILY_API_KEY": "<YOUR_ARGUS_TAVILY_API_KEY>",
"ARGUS_WOLFRAM_API_KEY": "<YOUR_ARGUS_WOLFRAM_API_KEY>"
}
}
}
}Ersetzen Sie die Werte in spitzen Klammern durch Ihre eigenen. Wir zeigen die Namen der Einstellungen, nie Werte.
Weitere optionale Einstellungen laut Marktplatz: ARGUS_DATA_ROOT, ARGUS_SEARXNG_BASE_URL.
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 | 1.6.4 | Forks (GitHub): 2 Sterne (GitHub): 5 |
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.
-
Make your knowledge agent-ready. One MCP endpoint, 5 connectors, 3 search modes.
-
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
-
Self-hosted, Tavily-compatible web search, extract, crawl and map tools for AI agents.
-
rag io.github.fieldcure/rag
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
-
mcp-knowledge-rag io.github.infoinlet-marketplace/mcp-knowledge-rag
Permission-aware RAG for agents — ingest docs, hybrid search, cited answers (hosted API).
-
Shared knowledge base for AI agents. Semantic search across agents, no setup required — just a URL.
-
Multi-step web research with citations via Perplexity's Agent API. Standard library only.
-
Scrape, crawl and search the web for AI agents via MCP.
-
Agent-native search engine with live web research optimized for AI agents.
-
Search and retrieve permission-aware knowledge from connected sources through Remly.
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)
-
Search, scrape, and crawl the web for AI agents. Batch scraping and answers with citations.
-
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…
-
HasData turns Claude Code into a research, lead-generation, and data-extraction agent. Instead of stitching together generic scrapers, the plugin gives Claude direct access to 40+…
-
openwebninja-universal-scraper
Extract structured data from 35+ public web APIs using natural language. Covers local businesses, jobs, products, reviews, news, social profiles, real estate, and finance. Outputs…
-
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 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…
-
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…
-
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…
-
Nimble web data toolkit — search, extract, map, crawl the web and work with structured data agents
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…
-
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…
-
Nimble web data toolkit — search, extract, map, crawl the web and work with structured data agents
-
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.
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Bring operational data and context into the flow of your ChatGPT conversations. You can ask questions, create and update records, and analyze your data—all through conversation…
-
General life-sciences research workflows with query routing, evidence synthesis, and optional parallel subagent analysis across genetics, omics, biology, chemistry, structure…
-
Answer product and business questions with data
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, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot…
-
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…
-
Create, connect, and interact with an AlloyDB for PostgreSQL database and data.
-
Create and retrieve from a Foundry IQ knowledge base using File, Azure Blob, or ADLS Gen2, then connect an existing Prompt or Hosted Agent.
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…
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Task Researcher and Task Planner for intermediate to expert users and large codebases - Brought to you by microsoft/edge-ai
-
Comprehensive collection for building declarative agents with Model Context Protocol integration for Microsoft 365 Copilot
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.
-
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.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
Gelistet auf Cursor: cursor/plugins (5)
-
Enrich people and companies, run AI research agents.
-
Search company knowledge and draft verified answers.
-
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.
-
Find and verify emails, discover companies, and save leads.
-
Search meetings and pull transcripts and summaries.
Gelistet auf Docker MCP Catalog (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…
-
Production-ready RAG service to search and retrieve data from your documents.
-
Connector for Perplexity API, to enable real-time, web-wide research.
-
tavily-mcp io.github.tavily-ai/tavily-mcp
MCP server for advanced web search using Tavily
-
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
Gelistet auf Official MCP Registry (5)
-
Make your knowledge agent-ready. One MCP endpoint, 5 connectors, 3 search modes.
-
Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.
-
Self-hosted, Tavily-compatible web search, extract, crawl and map tools for AI agents.
-
rag io.github.fieldcure/rag
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
-
mcp-knowledge-rag io.github.infoinlet-marketplace/mcp-knowledge-rag
Permission-aware RAG for agents — ingest docs, hybrid search, cited answers (hosted API).
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.