Get the latest curated crypto news headlines. Returns real-time news items with headline, sentiment, categories, and sources. Use the category parameter to filter by topic (e.g. 'bitcoin', 'defi', 'ai'). Call get_categories first to see all available category codes. Args: category: Filter by category code (e.g. 'bitcoin', 'ethereum', 'defi', 'ai'). Omit to get news across all categories. limit: Number of items to return (1-10, default 5).

Confirm an AI call after reviewing push-back questions, optionally providing answers to missing info. Required when ai_call returns state='pending_confirm'. Uses the original payment — no new payment needed. Returns call_id for polling with check_job_status(jobType='ai-call').

Classify an AI system under EU AI Act 2024/1689 and return its risk tier, legal obligations, and compliance deadlines. Use this tool when: - An agent needs to assess whether an AI system is legally permitted in the EU - A company is building or deploying AI and needs to understand its regulatory obligations - You need to identify prohibited AI practices (real-time biometric surveillance, social scoring, etc.) - You need to know applicable CISA alerts and cybersecurity requirements for AI systems Returns: risk_tier (prohibited/high-risk/limited-risk/minimal-risk), applicable_articles, legal_obligations, compliance_deadline, CISA_alerts, and recommended_actions. Example call: checkAiCompliance({ company: "Acme Corp", system: "Facial Recognition Attendance System", description: "Real-time facial recognition used to track employee attendance in a factory" }) Cost: $0.005 USDC per call.

Rank active AI/ML jobs against a candidate profile (skills, salary range, workplace, level). Scoring combines tag overlap (+2 per match), salary overlap (+3), workplace/level/type/location matches, and description keyword hits. Use this when an agent is choosing which role to surface to its user — it returns pre-ranked matches with scoring explanations.

AI-powered RAG chat, document analysis, and shareable summaries. Create chats, send messages, read AI responses, and generate shareable summaries. Works on both workspaces and shares. Side effects: chat-create and message-send consume AI credits (1 credit per 100 tokens). Destructive action: chat-delete permanently removes a chat. Actions & required params (all actions require profile_type + profile_id): - chat-create: type, query_text (workspace req'd, share optional) (+ optional: privacy, files_scope, folders_scope, files_attach, personality) - chat-list: (+ optional: include_deleted, limit, offset) - chat-details: chat_id - chat-update: chat_id, name - chat-delete: chat_id - chat-publish: chat_id - message-send: chat_id, query_text (+ optional: personality, files_scope, folders_scope, files_attach) - message-list: chat_id (+ optional: limit, offset) - message-details: chat_id, message_id - message-read: chat_id, message_id - share-generate: node_ids (workspace) | files (share) - transactions: (workspace only) - autotitle: (share only, + optional: context)

Quick AI visibility scan. Returns three scores: AEO Score (0-100, AI search engine findability), GEO Score (0-100, AI citation readiness), and Agent Readiness Score (0-100, AI agent interaction capability). Also returns AI Identity Card with mention readiness (0-100, predicts how likely AI will mention the brand), detected competitors, business profile (commerce/saas/media/general), and top 5 issues. 67+ checks across 12 categories. Free — no API key needed. Does NOT return per-check details or fix code — use audit_site for full breakdown, fix_site for generated fixes, compare_sites to benchmark against a competitor.

List chats (individual AI responses) for a project over a date range. Each chat is produced by running one prompt against one AI engine on a given date. Filters: - brand_id: only chats that mentioned the given brand - prompt_id: only chats produced by the given prompt - model_id: only chats from the given AI engine (chatgpt-scraper, gpt-4o, gpt-4o-search, gpt-3.5-turbo, llama-sonar, perplexity-scraper, sonar, gemini-2.5-flash, gemini-scraper, google-ai-overview-scraper, google-ai-mode-scraper, llama-3.3-70b-instruct, deepseek-r1, claude-3.5-haiku, claude-haiku-4.5, claude-sonnet-4, grok-scraper, microsoft-copilot-scraper, grok-4) Use the returned chat IDs with get_chat to retrieve full message content, sources, and brand mentions. Returns columnar JSON: {columns, rows, rowCount}. Columns: id, prompt_id, model_id, date.

Analyse a company's GitHub organisation for AI pivot signals: new AI/ML repositories, topic tag changes, star velocity, commit frequency, and contributor growth. Returns an AI adoption score. Use this tool when: - You need to verify whether a company is genuinely building AI (vs just talking about it) - A sales agent wants to time outreach to match a company's AI development phase - A research agent is assessing a company's technical capabilities and momentum - An investor wants to quantify a company's open-source AI activity as a due diligence signal Returns: ai_pivot_score (0-100), new_ai_repos, ai_topic_repos, total_stars_gained, commit_velocity, top_contributors, breakthrough_repos (fastest-growing), inferred_ai_focus_areas. Example: getGithubVelocity({ org: "microsoft", days: 30 }) → score 94, 8 new AI repos, 42k stars this month — HEAVY AI pivot. Cost: $5 USDC per call.

Run AI brand visibility scan across major LLM providers (async, poll with brand.scan.get).

Get a report on brand visibility, sentiment, and position across AI search engines. Results are aggregated for the entire date range by default. Use the "date" dimension for daily breakdowns. Returns columnar JSON: {columns, rows, rowCount, total}. Each row is an array of values matching column order. Columns: - brand_id — the brand ID - brand_name — the brand name - visibility: 0–1 ratio — fraction of AI responses that mention this brand. 0.45 means 45% of conversations. - mention_count: number of times the brand was mentioned - share_of_voice: 0–1 ratio — brand's fraction of total mentions across all tracked brands - sentiment: 0–100 scale — how positively AI platforms describe the brand (most brands score 65–85) - position: average ranking when the brand appears (lower is better, 1 = mentioned first) - Raw aggregation fields (for custom calculations): visibility_count, visibility_total, sentiment_sum, sentiment_count, position_sum, position_count When dimensions are selected, rows also include the relevant dimension columns: prompt_id, model_id, tag_id, topic_id, chat_id, date, country_code. Dimensions explained: - prompt_id: individual search queries/prompts - model_id: AI search engine (e.g. chatgpt-scraper, gpt-4o, gpt-4o-search, gpt-3.5-turbo, llama-sonar, perplexity-scraper, sonar, gemini-2.5-flash, gemini-scraper, google-ai-overview-scraper, google-ai-mode-scraper, llama-3.3-70b-instruct, deepseek-r1, claude-3.5-haiku, claude-haiku-4.5, claude-sonnet-4, grok-scraper, microsoft-copilot-scraper, grok-4) - tag_id: custom user-defined tags - topic_id: topic groupings - date: (YYYY-MM-DD format) - country_code: country (ISO 3166-1 alpha-2, e.g. "US", "DE") - chat_id: individual AI chat/conversation ID Filters use {field, operator, values} where operator is "in" or "not_in". Filterable fields: model_id, tag_id, topic_id, prompt_id, brand_id, country_code, chat_id.

Fetch performance data for AI/ML sector crypto tokens: NEAR, FET (Fetch.ai), AGIX (SingularityNET), RNDR (Render), WLD (Worldcoin), TAO (Bittensor), and the full AI token sector. Use this tool when: - An agent is investing in the AI token narrative and needs sector performance - You want to compare AI token performance vs BTC/ETH benchmark - A research agent is building a thesis on the AI crypto sector - An agent needs to identify which AI tokens are outperforming or underperforming Returns per token: name, ticker, price_usd, market_cap, 24h_change_pct, 7d_change_pct, 30d_change_pct, sector_rank, vs_btc_performance, narrative_tags. Example: getAiTokens({ limit: 10 }) → TAO +45% (7d), RNDR +28%, FET +18% — AI sector outperforming BTC this week. Cost: $0.005 USDC per call.

List all 34 available domain slugs grouped by cluster (CORE = AI/ML, APPLIED = scientific/industry). Call this before feed_post or artifact_publish to choose valid domain slugs.

Get a 24-hour AI-generated summary for any crypto ticker or topic (paid via x402). Returns decision-grade bullet points combining Gloria's curated news with real-time web search. Designed for fund managers and trading agents. Payment is handled via the x402 protocol using USDC on Base network. This tool returns the payment endpoint and instructions.

Returns Layer 3 sanity-check and validation prompts — the 'where AI gets financial modeling wrong' guidance. Use these to audit AI-generated work or catch common modeling errors.

Start generating a complete multi-chapter eBook using AI. Costs $0.45 per chapter (e.g., 10 chapters = $4.50). Returns a payment link that the user must visit to pay before generation begins. After payment, use get_job_status to track progress.

AI Economy Intelligence — aggregates ArXiv research + GitHub trending + job pivots + AI model prices + AI tokens + AI regulatory news into a comprehensive AI industry intelligence report. Use this tool when: - An AI-focused research agent needs a complete picture of the AI ecosystem in one call - A VC agent wants to assess AI industry momentum across research, hiring, and markets - You need to track AI adoption signals across multiple dimensions simultaneously - A strategy agent is building an AI market thesis and needs comprehensive inputs Returns: latest_arxiv_breakthroughs, github_trending_ai_repos, top_ai_hiring_companies, model_price_changes, ai_token_performance, regulatory_updates, ai_economy_momentum_score. Example: runBundleAiEconomy({ focus: "agentic ai autonomous" }) → 3 breakthrough papers on agents, top hiring: Anthropic/OpenAI/Google, Claude price cut 15%. Cost: $100 USDC per call.

Search real-time SEC filings (8-K, 10-K, 10-Q, S-1) for AI/autonomous operations mentions. Returns filings ranked by AI-relevance score with key extracted passages. Use this tool when: - A research agent needs to know what public companies are saying about AI in their official filings - An investor agent is identifying companies making material AI investments or disclosures - You need to detect new AI risk factors companies are disclosing to regulators - A compliance agent is monitoring for AI-related regulatory disclosures Returns per filing: company, ticker, form_type, filed_date, ai_relevance_score (0-100), key_passages, ai_keywords_found, material_disclosure (YES/NO), filing_url. Example: getSecFilings({ query: "large language model autonomous agents", forms: "10-K", days: 30 }) → MSFT 10-K: score 94, "$13B AI capex" passage flagged. Cost: $5 USDC per call.

IMPORTANT: call `cirra_ai_init` before calling any other tools of the Cirra AI MCP server. You MUST carefully read the instructions returned from this tool call before proceeding

Search knowledge entries by keyword (text match). Use query_knowledge for AI-powered answers.

Get the AI-optimized property manifest in schema.org format with lilo extensions. Available in YAML, JSON, or JSON-LD format. Use this for structured data integration and AI agent consumption.

Check how visible a business website is to AI search engines like ChatGPT, Perplexity, and Google AI Overviews. Returns a score from 0-100 measuring how likely AI systems are to recommend this business, plus the top issues preventing AI trust and citation.

Register a new AI agent in the agent registry. The agent will appear in tascan_list_agents and can receive dispatched tasks. Self-registration for AI agents joining the TaScan network.

Get AI coding tool adoption metrics including GitHub Copilot acceptance rate, Cursor active users, AI-generated code percentage, and suggestions per developer. Use this to understand how the team is using AI coding assistants and measure their impact on productivity. Read-only.

Search 1,000+ AI agent use-cases by task or goal description. Use-cases describe real-world workflows like "write a weekly report", "automate email replies", or "analyze sales data". Each use-case links to a dedicated page listing the best AI skills for that task. Use this tool when: (1) user describes a goal or workflow rather than a tool name, (2) user asks "how do I use AI for X", (3) you want to show what tasks AI can help with. Returns use-case slug, title, description, and page URL. Combine with search_skills to find specific tools for each use-case.

Get detailed profile for an AI company: total open roles, salary range, top tags/skills, workplace distribution, and apply URL. Use after list_companies or search_jobs to learn more about a specific employer.

Identify companies actively hiring for agentic AI roles from Greenhouse, Lever, HackerNews Who's Hiring, and Remotive. Job posting spikes are a strong buyer intent signal — companies building AI need AI tools. Use this tool when: - A sales agent wants to find companies in active AI build mode (highest conversion likelihood) - You need to detect which companies are expanding their AI teams right now - A market research agent is quantifying AI adoption by measuring hiring demand - A VC/investor agent wants to identify companies where AI is a strategic priority Returns per company: company_name, open_ai_roles_count, role_titles, avg_salary, seniority_mix, hiring_velocity (vs 30d_prior), inferred_ai_focus, recommended_tools_to_pitch. Example: getJobPivots({ roles: ["AI Engineer", "LLM Engineer"] }) → Stripe: 12 AI roles (up 4x), Shopify: 8, Figma: 6. Cost: $5 USDC per call.

Chain multiple AI operations in sequence. Output of each step is available to the next. steps: list of {action: str, params: dict} Available actions: research, summarize, analyze, sentiment, keywords, classify, rewrite, extract, qa, compare, outline, diagram, json_schema, workflow Use '{{prev_result}}' in params to reference previous step output. Example: [{"action": "research", "params": {"query": "AI trends"}}, {"action": "summarize", "params": {"text": "{{prev_result}}", "format": "bullets"}}]

Companies posting the most AI/ML jobs in the last N days. Complements get_stats trending_tags_7d — while that answers 'what skills are trending', this answers 'who's hiring most aggressively'. Returns company name/slug/logo plus the count of new jobs in the window.

Generate AI fashion product photography. Creates professional-quality product shots, on-model photos, flat lays, and editorial imagery. Uses Nano Banana 2 (primary) with Flux 2 Pro fallback. Costs 5 credits per image.

Issue a Human Authorization Protocol (HAP) credential to authorize an AI agent to act on a human's behalf. Creates a W3C Verifiable Credential 2.0 with scoped permissions, time-bounded validity, and a DataIntegrityProof signature. Requires authentication — the authenticated user becomes the credential owner.

AI Skill Store 개발자 계정을 등록합니다. 이메일 인증 후 API 키가 발급됩니다 (보안을 위해 즉시 발급되지 않음). Args: username: 사용할 username (영문/숫자, 3자 이상, 중복 불가) email: 인증용 이메일 주소 (필수 — 인증 링크가 발송됨) Returns: 등록 결과 메시지. 이메일 인증 후 API 키를 받을 수 있습니다.

Scan any website for AI visibility and marketing health. Returns scores for GEO (Generative Engine Optimization), Multimodal readiness, Agent-Ready infrastructure, and 6-dimension Marketing Health. Identifies critical findings with prioritized fix recommendations and revenue impact estimates.

Create AI-generated short-form video clips from a YouTube video or uploaded file. Returns a request ID instantly. Processing takes 5-30 minutes. Costs 1 credit.

Get an AI-generated news recap/summary for a specific category. Returns a concise narrative summarizing the most important recent news for the given category. Great for getting up to speed quickly. Args: category: Category code (required). Use get_categories to see options. Popular choices: 'crypto', 'bitcoin', 'ethereum', 'defi', 'ai', 'macro'. timeframe: Time window for the recap. Use '1h' for crypto/macro (updated hourly), '8h' or '24h' for other categories. Default '12h'.

List the search queries an AI engine fanned out to while answering prompts in a project over a date range. Each row represents one sub-query the engine issued for a given chat. Filters: - prompt_id: only queries from chats produced by this prompt - chat_id: only queries from this chat - model_id: only queries from this AI engine (chatgpt-scraper, gpt-4o, gpt-4o-search, gpt-3.5-turbo, llama-sonar, perplexity-scraper, sonar, gemini-2.5-flash, gemini-scraper, google-ai-overview-scraper, google-ai-mode-scraper, llama-3.3-70b-instruct, deepseek-r1, claude-3.5-haiku, claude-haiku-4.5, claude-sonnet-4, grok-scraper, microsoft-copilot-scraper, grok-4) - model_channel_id: only queries from this channel (openai-0, openai-1, openai-2, perplexity-0, perplexity-1, google-0, google-1, google-2, google-3, anthropic-0, anthropic-1, deepseek-0, meta-0, xai-0, xai-1, microsoft-0) - topic_id: only queries from chats whose prompt belongs to this topic - tag_id: only queries from chats whose prompt carries this tag Use get_chat with a returned chat_id to inspect the full AI response that produced these sub-queries. Returns columnar JSON: {columns, rows, rowCount}. Columns: prompt_id, chat_id, model_id, model_channel_id, date, query_index, query_text.

AI Skill Store 개발자 계정을 등록합니다. 이메일 인증 후 API 키가 발급됩니다 (보안을 위해 즉시 발급되지 않음). Args: username: 사용할 username (영문/숫자, 3자 이상, 중복 불가) email: 인증용 이메일 주소 (필수 — 인증 링크가 발송됨) Returns: 등록 결과 메시지. 이메일 인증 후 API 키를 받을 수 있습니다.

Find AI/ML tools and libraries by describing what you need in plain English. Searches 220K+ indexed AI repos via semantic + keyword search. Optional domain filter: mcp, agents, ai-coding, rag, llm-tools, generative-ai, diffusion, voice-ai, nlp, computer-vision, embeddings, vector-db, prompt-engineering, transformers, mlops, data-engineering, ml-frameworks Examples: find_ai_tool("database query tool for postgres", domain="mcp") find_ai_tool("autonomous coding agent") find_ai_tool("PDF document chunking for RAG pipeline")

List the product/shopping queries an AI engine fanned out to while answering prompts in a project over a date range. Each row represents one shopping sub-query and the distinct products returned for it in a given chat. Filters: - prompt_id: only queries from chats produced by this prompt - chat_id: only queries from this chat - model_id: only queries from this AI engine (chatgpt-scraper, gpt-4o, gpt-4o-search, gpt-3.5-turbo, llama-sonar, perplexity-scraper, sonar, gemini-2.5-flash, gemini-scraper, google-ai-overview-scraper, google-ai-mode-scraper, llama-3.3-70b-instruct, deepseek-r1, claude-3.5-haiku, claude-haiku-4.5, claude-sonnet-4, grok-scraper, microsoft-copilot-scraper, grok-4) - model_channel_id: only queries from this channel (openai-0, openai-1, openai-2, perplexity-0, perplexity-1, google-0, google-1, google-2, google-3, anthropic-0, anthropic-1, deepseek-0, meta-0, xai-0, xai-1, microsoft-0) - topic_id: only queries from chats whose prompt belongs to this topic - tag_id: only queries from chats whose prompt carries this tag Use get_chat with a returned chat_id to inspect the full AI response that produced these sub-queries. Returns columnar JSON: {columns, rows, rowCount}. Columns: prompt_id, chat_id, model_id, model_channel_id, date, query_text, products (array of product names).

Run a full AEO (Answer Engine Optimization) audit on a website. Returns a score 0-100, grade (A-F), breakdown by category (schema, meta, content, technical, AI signals), list of issues found, and prioritized recommendations to improve AI visibility. Use this when you need a comprehensive analysis of why a business isn't appearing in AI assistant answers.

Get Google's AI-generated responses (AI Overviews). Supports text queries. Returns AI-synthesized answers with source citations and reference links.

Submit feedback about an interaction with a Nordax-listed entity. Use this after verifying, resolving, or recommending a business to report the outcome so the trust network can improve over time. Feedback helps Nordax AI calibrate trust scores and entity rankings.

Generate a Cursor/IDE-ready prompt to fix AI readiness issues found in a report. Returns a comprehensive, actionable developer prompt. Pricing: Free with Pro subscription, or $0.002 USDC via x402 (anonymous or free-tier).

Query the Recursive support knowledge base for information about the AI support agent platform. Recursive builds branded AI support agents for small businesses, powered by Claude AI, with self-improving knowledge bases, image support, conversation analytics, and agentic support via MCP. Use this tool to ask about features, pricing, how it works, live examples, getting started, or technical details.

Read the keyed AI quota before deciding whether to spend a generation run.

Run LLM deep analysis on a completed report. Returns detailed AI analysis with priority issues and actionable recommendations. Pricing: Free with Pro subscription, or $0.005 USDC via x402 (anonymous or free-tier).

List entities of a specific type/category in a location. Great for questions like 'What restaurants are in Nashville?' or 'Find dentists in Austin, TX'. Results are ranked by verification tier and AI visibility score.

Check whether a website is properly configured for AI crawler access. Checks robots.txt for AI bot blocks, presence of llms.txt, schema markup, and other signals that affect whether ChatGPT, Claude, Perplexity and other AI assistants can read and cite the site. Returns a readiness summary with specific blockers.

Manage connections to Salesforce orgs associated with the user's Cirra AI account. Call cirra_ai_init at least once before using this tool.

Generate a complete manufacturing tech pack with measurements, materials, BOM, construction steps, size chart, and colorways. Uses Claude AI for fashion-specific technical specifications. Costs 50 credits.

URLを指定すると、そのサイトがAIエージェント（GPT/Claude/Gemini等）からどの程度「見えている」かを診断する。llms.txt、robots.txt(AIクローラー許可)、構造化データ(JSON-LD)、OGPメタタグ、寸法データ表記、越境対応度をチェックし、0-100のスコアとA-Fグレードを返す。越境対応度(cross_border_readiness)は海外AIエージェントへの可視性を評価。AIOエージェンシーのデモとして「御社の商品、AIからこう見えています」と提示できる。

Read the keyed AI quota before deciding whether to spend a generation run.