Web Search

Crypto market intelligence: prices, funding rates, narratives, regime, and delta-neutral research.

Cross-market (US/JP/KR) structured financials, segments, ownership & metrics, traceable to filings.

AI visibility + fact-checks (ChatGPT/Perplexity), review gaps & competitor scans, local SEO.

Live web search and clean-markdown page fetch over the Keenable web index.

Fast, intelligent web search and web crawling. New mcp tool: Exa-code is a context tool for coding

MCP server registry — validated by live handshake, scored on reliability, monitored continuously.

Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.

Live web search, image search, topic filters and full-text fetch over our own crawled index.

Search rankings, clicks, and indexing for your site — in chat.

CrawlForge MCP Server - Professional Model Context Protocol server with 29 web scraping, crawling, deep-research, and autonomous-extraction tools. Returns clean Markdown and structured JSON for Claude, Cursor, and any MCP client. Defaults to local Ollama

Multi-source web search for LLM grounding — works with any model provider

Local-first web intelligence MCP server for AI coding agents

Pay-per-call agent superpowers: media/video gen, product demos, research, GTM, scraping, compute.

MCP server for web search that returns verbatim passages from sources instead of summaries. Passage-level ranking with source authority, no LLM in the loop.

LLM chat, text tools, image generation, editing and batch image jobs

Official Model Context Protocol (MCP) server for Annolux — Curated English & Chinese Web Search for AI Agents with explicit fetched_at timestamps

The web data platform for AI agents — fetch, search, crawl, extract, monitor, screenshot. 55+ domain extractors, 65-98% token savings, MCP server included. One API call.

One MCP server for all web data. Search, scrape, crawl, proxy, and AI research in one install.

Eval-backed tool discovery for AI agents on the auxiliar.ai web-access gateway. recommend_tools picks the best search, scraping, browser-automation or voice provider for a job from measured benchmarks (quality, latency, cost, error rate), returning routes

Turn messy input into a sourced report. 15 default tools: workflow, bidirectional sync, canonical NodeBench research bridge, discover_tools, and load_toolset.