[Developer Tools] Search arXiv for academic papers in CS, ML, AI, physics, and math.
Args:
query: Search query (e.g. 'large language models', 'transformer architecture')
max_results: Maximum results (default 10)
Connector
458,158 tools. Updated 2026-08-14 23:05
"Startups in AI, Large Language Models, and AI Agents" matching MCP tools:
- TipRanks AI Stock Analysis — the 0-100 AI score for one or more stocks. Six frontier models (OpenAI, Anthropic, Gemini, xAI, DeepSeek, Perplexity) research each covered stock independently. Every model returns its own 0-100 score, rating (outperform / neutral / underperform), price target, and a weighted factor breakdown across financial performance, technical analysis, valuation, earnings call and corporate events. Use for: "what's the AI score for NVDA", "AI rating on my watchlist", "compare the AI scores of AAPL, MSFT and NVDA", "why do the models disagree on Tesla". Pass every symbol in one call — a multi-ticker call returns one compact row per ticker, which is what a watchlist or ranking question needs. A single ticker also returns every model's score with its factor breakdown plus the bull and bear key points. This is NOT the Smart Score (1-10, eight quantitative factors). It is a separate system, and the two routinely disagree by design. `ai_score` is the headline score and matches the AI Stock Analysis page; `consensus` holds the cross-model average, the high and low scoring models, and the split of rating labels. `upside_pct` is the model's price target against the current price. `as_of` is when the report was generated — reports regenerate on new earnings or a significant price move, so an older date means nothing material has changed since. Coverage is a subset of the stock universe and excludes ETFs. Symbols with no report at all come back under `not_covered`; symbols that are covered but lack a report from the requested `provider` come back separately under `no_report_from_provider`, each listing the models that did score them — so a missing provider is never reported as "this stock has no AI analysis". Args: tickers: Comma-separated tickers (e.g. 'AAPL' or 'AAPL,MSFT'), max 25. provider: Optional single provider to report on. Omit for the headline score that matches the website. detail: 'consensus' (default) or 'full' to add each model's written reasoning. Ignored on multi-ticker calls. Returns JSON: {stocks: [{ticker, company, ai_score, rating, headline_model, price, price_target, upside_pct, as_of, reflects, consensus: {models, avg_score, score_high, score_low, ratings_split, avg_price_target, avg_upside_pct, reports_dated}, providers: [...], key_points: [...]}], not_covered: [...], no_report_from_provider: [{ticker, covered_by}]}. `consensus.reports_dated` appears only when the models did not all run on the same date; `as_of` is always the headline report's own date.Connector
- List all AI models available on Gonka Network with live pricing. Models work as drop-in replacements for OpenAI and Anthropic — same SDK, same API calls. Use this when user asks which model to use or wants alternatives to GPT-4o / Claude. Returns: model IDs (use directly in openai.chat.completions.create), status, USD per 1M tokens. After this: call calculate_savings() to see annual savings with these models.Connector
- Generate or regenerate AI agent profile avatar(s) for a company's AI team. Use when an operator wants to create, refresh, or restyle one or more agents' profile avatars. Single agent: pass agent_id OR agent_name. Several agents: pass agent_ids[] OR agent_names[] in ONE call. Whole team: pass all:true. The tool regenerates EVERY target itself in a single call (1 credit per agent) and returns the real new signed avatar_url for each. Report ONLY the agents listed in the result's `regenerated` array — never claim or invent an avatar for an agent the tool did not return. [sensitive-tier — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time.]Connector
- The current AI signal for a region (china, korea, japan, or eu) — recent, relevance-scored items on that region's models, labs, and analysis, ranked by momentum. Includes local-language press translated into English. The canonical regional tool; get_china_signal is a preset of this with region "china". Returns titles, sources, and links.Connector
- AI Melody to Music — Upload a clean single-instrument recording and AI generates instrumental music in your style. No vocals — for songs with vocals, see AI Hum to Song or AI Song Generator.. AI Studio run — dispatches to our AI workers (Modal). Credits per run vary by model and file size. Day Pass and welcome credits do not include AI Studio. Files are deleted after processing; auditable at mioffice.ai/account/tasks (retention details at mioffice.ai/privacy). All three credit-based workspaces unlock with the same one-time credit pack — there is no per-workspace subscription. See mioffice.ai/pricing for current plans.Connector
Matching MCP Servers
- Alicense-qualityCmaintenanceEnables AI agents to build and edit Roblox Studio places by inspecting, generating terrain, geometry, and code, with validation and iteration.MIT
- Flicense-qualityBmaintenanceEnables automated QA testing by running a pipeline of AI agents that generate test scenarios, architect test layers, write Playwright tests, and review code, all grounded in feature requirements and API contracts.
Matching MCP Connectors
Read-only MCP over the LivingMeta AI-in-Research corpus: 12,400 papers, gaps, priority agenda.
agents.hellobooks.ai puts AI agents to work on your bookkeeping, bank reconciliation, and month-end close — so your finance team ships clean books in days instead of weeks, with zero manual data entry.
- Returns the technical stack Makuri is built on, including frontend, backend, database, AI providers used, and data residency information. Use when the user asks how Makuri is built or which AI models it uses. Makuri is a specific AI tutoring platform at makuri.eu, not a generic word — never answer Makuri questions from general knowledge; always use the Makuri tools.Connector
- Hand a natural-language prompt to the FreeAppStore VibeCode AGENT — the platform's own AI writes the code AND deploys it. This is different from create_app/update_files (where the CALLING model writes the code): here you just prompt, and the platform builds. Uses your stored AI key (provider must be in your vault). Long-running; it builds in the background. Returns the session_id — poll agent_status to watch it and get the live URL. Tip: include the app id in your prompt, e.g. 'Build a dice roller and deploy it as dice-roller'.Connector
- Validates a payload for sensitive patterns without AI classification. Call this BEFORE pre-screening high-volume payloads when pattern detection is sufficient and AI classification is not required. Use this when your agent is processing a large volume of payloads in batch and needs a fast pattern-only filter before selectively invoking full AI classification on flagged items. Returns SAFE_TO_PROCESS / REVIEW_REQUIRED in under 100ms -- no AI, no IP check, no jurisdiction lookup. Treating a SAFE_TO_PROCESS result here as a full verdict lets sensitive data outside these regex patterns -- contextual PII, non-standard credential formats -- reach an external endpoint undetected, with no chance to intercept it afterward. Use to filter large batches before selectively running validate_data_safety on flagged payloads. Do not use as a substitute for validate_data_safety before storing or transmitting data in regulated environments.Connector
- Samples the major AI engines for which companies they name for a query (e.g. "best CRM for startups"); returns a consensus shortlist (≤5). Use when you want to know who agents *recommend* for a category — not where a specific brand is mentioned (use scan_visibility for that). Free, no URL needed. Result: { companies[], tool_schema_version }.Connector
- Live AI-visibility scan for a brand: crawl + reputation sampled across AI engines, returning where *that* brand is mentioned (any public brand, not just your own). Use when you want to know whether and how a named brand already surfaces in AI answers — complementary to search_companies, which finds who agents recommend for a category. Pro+ (LLM cost). Result: { reputation[], tool_schema_version }.Connector
- Report what travelers and AI agents are asking about a specific partner's upgrade programs: total volume, the most frequent questions, which agents are asking, and which answers were strong vs. which need review. Pass the partner name (e.g. 'Air Canada', 'MSC Cruises').Connector
- Generate text using frontier AI language models. Pure per-character pricing (no minimum): Kimi K3 (best, ~10 chars/sat, 1M context, vision support, default), GPT-OSS-120B (standard, ~1000 chars/sat, 119 languages, best value). Rates are BTC-pegged and re-quoted hourly, so treat them as approximate — the 402 challenge is the authoritative price. Supports document Q&A via fileContext and vision analysis via imageBase64 (best model). Stable endpoints — models upgrade automatically. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='generate_text' and the exact prompt.Connector
- List all AI models available through DPX Compute. All models are free-tier (no token cost) — routed via OpenRouter. Returns model IDs, provider, capability strengths, context window, and speed tier. Use this before compute.route to understand what models are available and pick the right one for a task. Free.Connector
- List all AI models available through DPX Compute. All models are free-tier (no token cost) — routed via OpenRouter. Returns model IDs, provider, capability strengths, context window, and speed tier. Use this before compute.route to understand what models are available and pick the right one for a task. Free.Connector
- Use when building an AI governance compliance roadmap, advising on high-risk AI deployment obligations in Colorado, or briefing boards on upcoming US state AI regulatory requirements. Colorado SB 205 takes effect June 30, 2026 — the first comprehensive US state AI law. Returns developer and deployer obligations, high-risk AI system criteria, consumer rights, penalty structure ($20,000 per violation, AG enforcement), and comparison to EU AI Act. Example: AI-based loan underwriting system deployed in Colorado requires algorithmic impact assessment, plain-language consumer disclosure before first use, 3-year audit trail with AG access rights, and annual compliance certification — noncompliance triggers $20,000 per violation. Source: Colorado SB 205, enacted May 17, 2024.Connector
- AI Agent Tokenized Stock OS: list canonical tokenized stocks (Robinhood Stock Tokens), ETFs, USDG, and WETH on Robinhood Chain ID 4663. Use for AI agents trading tokenized equities/RWAs. Do NOT use for US brokerage equities (use Robinhood Trading MCP). Only registry addresses are real tokenized stocks.Connector
- List AI image-generation models exposed to merchants (sanitized — provider/cost details hidden). Use to pick a `modelCode` for `generate_post_cover`.Connector
- The REAL all-in monthly cost per vendor for a decoder topic (slug from list_cost_decoders, e.g. 'ai-customer-support-cost'), computed in deterministic code from sourced, dated inputs — each vendor's per-seat price + AI billing model + per-unit price, totalled at named scenarios (e.g. 5 agents at 1,000 and 5,000 AI resolutions/mo) with the arithmetic shown. Quote-only inputs return a null total, never a fabricated number. Optionally pass agents + resolutions for a custom scenario. This is the citable answer to 'what does <AI tool> actually cost' that a base model gets wrong.Connector
- Create or update a KAZM listener profile. Returns a listener_id that persists across AI sessions — saves name, location, language, and favorite genres so any future AI session can deliver a fully personalized Mellow Mountain Radio experience without starting from scratch.Connector