"Deep Think: Exploring Deep Thinking Concepts" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Your agent needs the open web — searched by more than one engine, and read as clean markdown rather than raw HTML. **What you can ask for** • "Search this question with two providers and tell me where they disagree." • "Scrape these 40 URLs into markdown, in one batch." • "Crawl this documentation site and give me every page." • "Do deep research on this topic and cite the sources." • "Find the academic papers behind this claim." **How to use it** Point any MCP client at https://mcp.aisa.one/search/mcp and sign in with OAuth — there is no key to create or paste. 30 tools across several independent providers: Tavily and Exa search, answers, contents and agent runs; Firecrawl scrape, batch scrape, crawl, map and search; Perplexity Sonar, Sonar Pro, reasoning and deep research; Oxylabs AI search and LLM jobs; OpenAI and Anthropic web search; and scholarly search. **Why this rather than the source** Several independent indexes behind one account, because one engine's blind spot is not visible from inside it. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Find the page here, then ask the same agent who links to it or how much traffic it gets — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/seo-serp/mcp for the Google results page itself, https://mcp.aisa.one/seo-serp-other-engines/mcp for Bing, Baidu and Naver.
Can I use this URL for RAG, summarize it, train on it or index it? Check observed RSL declarations and machine-readable usage/licensing terms before processing supported content. Use acqpath_capabilities first; acqpath_rights_quote prepares a private quote. Stable HTTP: https://api.getacqpath.com/v1/rights/preflight — no AcqPath account or API key. Fresh 0.02 USDC, deep 0.05 USDC on Base; verified signed offer authoritative. Public payment uses acqpath-request-binding nonce support or the configured AcqPath SIWX adapter for official TS/Python x402 signers. Generic zero-config clients remain unsupported; mainnet paid E2E is unverified. No paid crawl purpose. UNKNOWN is not permission; no license, legal clearance or legal advice. The legacy acqpath_quote routing tool is disabled. Keep private claims outside model context. Integrate: https://developers.getacqpath.com/from-glama
Search, browse, and buy 597 AI thinking frameworks, Tools and bundles from within any MCP client.
Search EU legislation, CJEU case law, and treaties; traverse CELLAR graph; browse EuroVoc concepts.
Structured restaurant intelligence for AI platforms. 760K+ restaurants catalogued across 26 countries, 62K+ with deep 37-dimension analysis including letter grades, occasion-aware recommendations, menu insights, and neighborhood exploration. Six tools: find restaurants by name, search by location, explore area dining scenes, look up detailed profiles (3 detail tiers), ask natural language questions, and get personalized recommendations.
Objective-driven deep research for AI agents, paid per request via MPP (Tempo mainnet USDC.e) - no account or API key. Free daily-limited quick search across global news and arXiv papers. Paid deep research: send an objective, get an exact quote with a planned source list, pay the challenge, and poll a tracker for a cross-source report from a real cloud Chromium browser plus AI synthesis. Optional notify_email delivers the report by email. No CAPTCHA, login, or paywall bypass.
Pre-build reality check for AI coding agents. Scans GitHub, Hacker News, npm, PyPI & Product Hunt — returns a 0-100 reality signal before you build. Supports quick (2 sources) and deep (5 sources) parallel search.
The Balanced Investor Club, the thinking companion for the markets. Educational, not advice.
Objective-driven deep research: free daily quick search plus MPP-paid cross-source browser reports.
4 web-search tiers (x402 USDC on Base) - simple/medium/deep/cached. Free health.
VibeMarketing (https://vibemarketing.ninja/mcp) is a directory service that catalogs and provides information about various MCP (Model Context Protocol) servers. It serves as a centralized resource where users can discover different MCP servers and their capabilities. Examples of servers listed in the directory include Sequential Thinking MCP (for dynamic problem-solving through structured thought sequences) and Memory MCP (a knowledge graph-based persistent memory system).
Read-only MCP server for searching and browsing essays on payments, fintech, and protocol thinking by Ben Milne. 3 tools: list_posts, get_post, search_posts. Streamable HTTP transport, no auth required.
Sniff out deep company intelligence on any domain
Baselight’s MCP server lets you seamlessly integrate your favourite applications with the Baselight platform. By connecting to the MCP server, you can browse, discover, and query 70,000+ datasets and 450+ billion rows directly from your preferred environment—whether you’re building, analysing, or exploring.
Parse dreams into structured context and search DreamGraph concepts without storing dream text.
Check the factual claims in a draft or an answer: a quick verdict, or a deep check with sources.
Find relevant Smart‑Thinking memories fast. Fetch full entries by ID to get complete context. Spee…
Grounded synthesis from public sources. 3 free calls total; then $0.10 brief or $0.25 deep via x402.
Search 161 dark/deep data sources across 25+ domains that Google can't reach. 6-step pipeline methodology for intelligence gathering. Streamable HTTP endpoint.
Make your knowledge agent-ready. Connect docs from Confluence, Notion, GitHub, Dropbox, or Google Drive — any AI agent searches them via one MCP endpoint. 3 retrieval modes: vector search, broad search, and full document access. The agent decides how deep to dig.
