MCP servers · shortlist
MCP servers for search and extraction
Web search, crawling and scraping servers for retrieval pipelines. If your agent needs current information rather than training data, this is the layer that provides it.
How this list was ordered. There is no reliable popularity signal in the source registries, so entries are ranked by how completely the record is documented — a substantial description plus a documentation, repository or base URL — and then alphabetically. 235 mcp servers in this scope clear the content bar; the top 24 are shown. A place here is not an endorsement or a paid slot.
Shortlisted entries
- 01
RipperMercs/tensorfeed
Real-time AI industry intelligence MCP server. 6 free tools (AI news, service status, model pricing, today summary, agent activity, MCP registry snapshot) and 13 paid premium tools (routing recommendations, news search, history series, cost projection, provider deep-dive, model comparison, agents directory, what's new brief, MCP registry series, webhook watches with daily/weekly digest tier). Pay-per-call in USDC on Base mainnet, no accounts. npx -y @tensorfeed/mcp-server
Aggregators auth: None
- 02
inth3shadows/terse
Transparent proxy that sits in front of any other MCP server and shrinks its tool output before it reaches the model. Lossless by default — a denser encoding of the same bytes, with a round-trip gate asserting an exact inverse, so nothing is dropped or summarised. Repeated calls to the same tool emit a delta against the prior result instead of the whole payload. Per-tool opt-in, no decode step, no model in the loop. uv tool install terse-mcp then terse proxy -- <server>
Aggregators auth: None
- 03
Correctover/mcp-server
Contract validation and self-healing failover for LLM APIs. 6-dimension verification (structure, schema, latency, cost, identity, integrity) in 22μs P50. 87 self-healing rules with MAPE-K autonomic loop. BYOK direct connect to 9 providers (OpenAI, Anthropic, DeepSeek, Moonshot, Zhipu AI, Qwen, SiliconFlow, Groq, Together AI). L3 failover in 949ms E2E. Install: npx -y correctover-mcp-server.
Aggregators auth: None
- 04
scotia1973-bot/api-hub
Memory Vault: 49 MCP tools with persistent agent memory (store/recall/search), plus 45 utility tools (QR codes, crypto prices, weather, DNS, geolocation, passwords, UUIDs, text, finance, code). Free tier + $2.99/mo Pro. Install: pip install gadgethumans-api-hub-mcp or uvx gadgethumans-api-hub-mcp. Hosted at api.gadgethumans.com/mcp.
Aggregators auth: None
- 05
codeislaw101/katzilla
Unified data API for AI agents — 300+ free, public, and government data sources behind a single API key. Access economic (FRED, BLS), environmental (EPA, NOAA), health (CDC, FDA), weather (NWS), financial (SEC, CFPB), science (NASA, arXiv), and 30+ more categories. Install: npx @katzilla/mcp.
Aggregators auth: API Key
- 06
sascharo/gxtract
GXtract is a MCP server designed to integrate with VS Code and other compatible editors. It provides a suite of tools for interacting with the GroundX platform, enabling you to leverage its powerful document understanding capabilities directly within your development environment.
Search & Data Extraction auth: None
- 07
retracn/automationnation-mcp
17 data tools backed by Apify Actors: Google Flights and Hotels prices, Google Shopping, News, Images, Videos, Jobs and Trends, YouTube transcripts, Google Maps leads, Ads Transparency, app reviews and AI-search visibility; pay per result with a spending cap on every run.
Search & Data Extraction auth: None
- 08
webpeel/webpeel
Smart web fetcher for AI agents with auto-escalation from HTTP to headless browser to stealth mode. Includes 9 MCP tools: fetch, search, crawl, map, extract, batch, screenshot, jobs, and agent. Achieved 100% success rate on a 30-URL benchmark.
Search & Data Extraction auth: None
- 09
XZXZZX-Ai/bilibili-mcp
Local-first Bilibili MCP server for video metadata, subtitles and structured transcripts, chapters, popular comments, and optional local ASR fallback. Published on npm as @xzxzzx/bilibili-mcp with bilingual documentation.
Search & Data Extraction auth: None
- 10
firecrawl/firecrawl-mcp-server
Official Firecrawl server to search the web and scrape, crawl, map, and extract structured data from any site for LLMs. Handles JS-rendered pages, PDFs, and batch jobs; hosted remote MCP with OAuth or self-host.
Search & Data Extraction auth: OAuth
- 11
Darko893/haunt-mcp-server
Haunt web extraction for AI agents: structured JSON or clean Markdown from permitted public pages, including Cloudflare-protected ones, with honest blocked/login/captcha errors instead of fabricated data
Search & Data Extraction auth: None
- 12
tigranbs/mcgravity
A proxy tool for composing multiple MCP servers into one unified endpoint. Scale your AI tools by load balancing requests across multiple MCP servers, similar to how Nginx works for web servers.
Aggregators auth: None
- 13
TechMap/mcp.techmap.io
Search and count job postings from 185 sources in 250 countries (~8M new per month) via Techmap's Jobs API; filters for title, skills, company, city, remote/hybrid, salary and posting date.
Search & Data Extraction auth: None
- 14
malamutemayhem/unclick
The universal remote for AI: one MCP install gives any compatible agent 450+ callable endpoints across 60+ integrations, plus persistent cross-session memory. npx @unclick/mcp-server
Aggregators auth: None
- 15
DasDigitaleMomentum/searxNcrawl
Web search via your own SearXNG instance and/or You.com, plus page and site crawling to deduplicated Markdown with Crawl4AI and Playwright, including pages behind a login.
Search & Data Extraction auth: None
- 16
StripFeed/mcp-server
Convert any URL to clean, token-efficient Markdown for AI agents. API-backed extraction with token counting, CSS selector support, and configurable caching via StripFeed.
Search & Data Extraction auth: API Key
- 17
MarcinDudekDev/the-data-collector
MCP server for scraping Hacker News, Bluesky, and Substack with x402 micropayment support. Tools: hnsearch, blueskysearch, substacksearch. $0.05/call via USDC on Base.
Search & Data Extraction auth: None
- 18
Alepha188838884/context-firewall
Local MCP proxy that merges downstream servers behind a few meta-tools with progressive discovery and compresses large tool outputs, with full output on demand.
Aggregators auth: None
- 19
Continuum-AI-Corp/orcarouter-mcp-server
Browse LLMs from OpenAI, Anthropic, Google, Qwen, DeepSeek and others with live prices, and route chat completions through the OrcaRouter gateway with fallback.
Aggregators auth: None
- 20
profullstack/mcp-server
Developer utilities: SEO optimization, document conversion, domain lookup, email validation, QR codes, weather data, social media posting and security scanning.
Aggregators auth: None
- 21
withoneai/mcp
Search, document and execute authenticated API calls across apps such as Gmail, Slack, Stripe, Notion and GitHub through a few tools with constant context size.
Aggregators auth: None
- 22
Aganium/agenium
Bridge MCP servers to the agent:// network so other agents can discover and call their tools, with DNS-like identity, mTLS, trust scores and capability search.
Aggregators auth: None
- 23
api7/aisix
Self-hosted MCP gateway fronting upstream servers with per-tool access control, guardrails, rate limits and usage logs; also proxies LLM and A2A agent traffic.
Aggregators auth: None
- 24
daedalusdevelopmentgroup/ddg-agent-payable-services
Pay-per-call x402 tools (utilities, DNS/WHOIS, blockchain RPC, market and DEX data, prediction markets, security audits) plus an OpenAI-compatible LLM gateway.
Aggregators auth: None
github.com/daedalusdevelopmentgroup/ddg-agent-payable-services ↗
Snapshot 2026-10-19. Fields shown are what the source registry stated, not a live probe — check the linked documentation before integrating. See the methodology.