- NewsBlog Composer @mohammed-jameal-j/newsblog-composerVerifies news stories, mines SEO keywords, builds schema and reviews your draft. You write it.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- ResearchZosho @wyrdsekai/researchzoshoDeep research assistant that checks its citations against the sources and keeps what it found.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- MyWebSearch @wtznicy/my-websearchMyWebSearch - multi-engine web search MCP server, CLI and local daemon. No API keys required.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- PriceOracle @tooloracle/priceoraclePriceOracle - 7 dynamic pricing tools: elasticity, A/B, segment pricing, competitor scan.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- DLBrowser @dekryptlabs/dlbrowserSelf-healing web access for AI agents — recovers through bot blocks, captchas and JS pages.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Yandex search @johnisanerd/yandex-searchYandex search results, images, and SERP data via the Apify Yandex Search Scraper, hosted MCP.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
- Tokenguard @eltociear/tokenguard-mcpReal-world data for agents: air quality, geocoding, quakes, holidays, web search5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Decodo @pipeworx-io/decodoDecodo MCP — wraps the Decodo Web Scraping API (decodo.com, formerly7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Agent Media Toolkit @krakonjac300-pixel/agent-media-toolkit15 media & data tools for AI agents: search, transcribe, subtitles, voiceover, translate & more.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- CatchAll @newscatcherapi/catchallWeb search API: find every relevant event across the open web, not just the top results.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- AIMarket MCP Gateway @alexar76/aimarket-mcpStdio + HTTP MCP gateway: SSRF-hardened web_fetch, web_search, metis_verify, market_search.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Vectora @brunosrz/vectoraAI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Superhighway @patwalls/superhighway-mcpWeb search for AI agents — 5 tools: search, news, images, scrape, research. x402/USDC or API key.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Perplexity Polza @ivanantigravity-lgtm/perplexity-polza-mcp-serverPerplexity MCP server backed by the Polza.ai chat completions API.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Groundhog @dmytrome/groundhog-mcpSearch, read and research the web, with hidden text stripped by default and sources hashed5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- SearXNG Deepdive @burakaydinofficial/searxng-deepdiveMCP server for SearXNG with engine targeting, multi-page fanout, and HTML→Markdown URL reading.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Sofya @sofya/sofyaWeb search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Lithtrix — Identity, Memory & Trust for AI Agents @lithtrix/lithtrix-mcpIdentity, memory, trust, and swarm primitives for AI agents. MIRC base always free.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Vee3 @vee3io/vee3Hosted MCP with 91 agent tools: X, domains, SEO, Maps, Trends, Search, YouTube, TikTok, and more.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Web search @groundroute/web-searchWeb search for AI agents — one tool across 6 engines, routed to the cheapest + cached.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
- Firecrawl @pipeworx-io/firecrawlFirecrawl MCP — wraps the Firecrawl API (firecrawl.dev) for web6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Secant Agent Research Pack @jnilrac/secant-agent-research-mcpPaid MCP web research for agents: search, extraction, citations, and x402 payment discovery.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Giskard Search @giskard09/searchPay-per-use web search for AI agents. Lightning invoice, Ed25519 signature, karma discounts.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Kael MCP Server @dreamingms/kael-mcp-server16 AI-native tools with dual SSE + streamable-http transport. Free tier available.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
