Create a single node in a deployed graph project. REQUIRES: Project must be deployed (use deploy_graph_staging first). The entity_type must match an entity key from the project schema. Use get_graph_data_schema to see available entity types and their fields. Example: entity_type: "person" entity_id: "alan-turing-001" data: {"name": "Alan Turing", "birth_year": 1912, "field": "Computer Science"} The entity_id is your unique identifier — use meaningful IDs for knowledge graphs.

Create a new computer vision project. Returns the created project's id, name, type, and url.

Search the arXiv preprint repository for peer-reviewed academic papers in physics, mathematics, computer science, and related fields. Returns paper title, author list, abstract, publication date, PDF link, and category classification. Use for cutting-edge research, literature review, or staying current in academic fields.

Search arXiv for academic papers in computer science, machine learning, AI, physics, and mathematics. Returns paper titles, authors, abstracts, submission dates, and direct PDF download links. Use for researching algorithms, ML techniques, or emerging CS topics.

Search Google Scholar for computer science research papers, citations, and academic publications. Returns paper title, authors, publication details, citation count, and link to paper. Use for finding research on CS topics, reviewing state-of-the-art, or citation tracking.

Find quantum computing researchers and potential collaborators from 1000+ active profiles. Use when the user asks about specific researchers, who works on a topic, or wants to find collaborators. NOT for jobs (use searchJobs) or papers (use searchPapers). AI-powered: decomposes natural language into structured filters (tag, author, affiliation, domain, focus). Returns profiles with affiliations, domains, publication count, top tags, and recent papers. Data from arXiv papers published in the last 12 months. Max 50 results. Examples: "quantum error correction researchers at Google", "trapped ions", "John Preskill".

Fetch full details of a single participant from a sweepstakes by token, email, or phone. At least one search parameter is required. Use fetch_sweepstakes first to get the sweepstakes_token. For listing participants, use fetch_participants instead. NEVER fabricate, invent, or hallucinate participant data under any circumstance. If no result is returned by the API, report exactly that — do not guess names, emails, or counts. Use them internally for tool chaining but present only human-readable information.

Change the resolver contract for an ENS name. The resolver is where a name's records live (ETH address, text records, content hash, etc.). Changing the resolver points the name at a different contract. Common use cases: - Migrating to the latest ENS Public Resolver - Pointing to a custom resolver (e.g. for off-chain/CCIP-read resolution) - Fixing a name that has no resolver set Pass "public" as the resolver address to use the ENS Public Resolver (0x231b0Ee14048e9dCcD1d247744d114a4EB5E8E63). WARNING: Records on the old resolver won't be visible after switching. Set up records on the new resolver first, or use the ENS Public Resolver which most names already use.

List all BART stations with abbreviation codes and locations. Use this to look up station codes needed by other tools.

Get today's quantum computing papers from arXiv — no parameters needed. Use when the user asks "what's new in quantum computing?" or wants a daily paper briefing. Returns the most recent day's papers with title, authors, date, AI-generated hook (one-line summary), and tags. For date-range or topic-filtered search, use searchPapers instead. Use getPaperDetails for full abstract and analysis of a specific paper.

Instant community signal — no registration, no key. Just slug + direction. Use when you want to quickly express trust (up) or distrust (down) on any entity. Community favors are 0.1x weight. For 10x weight, use nanmesh.trust.review instead.

Get detailed information about a specific job listing/posting by its job listing ID (not application ID). Use this to view the full job posting details including description, salary, skills, and company info. For job application details, use get_application instead.

Search the Nova Scotia Open Data catalog (data.novascotia.ca) for datasets by keyword, category, or tag. Returns dataset names, IDs, descriptions, column names, and direct portal links. Use list_categories first to see valid category and tag names. Use the returned dataset ID with query_dataset or get_dataset_metadata for further exploration.

[tourradar] Search for tours by title using AI-powered semantic search. Returns a list of matching tour IDs and titles. Use this when you need to look up a tour by name. When you know tour id, use b2b-tour-details tool to display details about specific tour

Fetch live crypto market data from CoinGecko and DexScreener. No external data needed — WaveGuard pulls it for you. Use 'coin_id' for CoinGecko (e.g. 'bitcoin', 'ethereum', 'solana'). Use 'contract_address' for DexScreener (any chain). Use 'search' to find token IDs by name/symbol. Returns: price, volume, market cap, liquidity, price history, OHLC candles — ready to feed into waveguard_token_risk, waveguard_volume_check, or waveguard_price_manipulation.

Get entry page settings for a sweepstakes. Use fetch_sweepstakes first to get the sweepstakes_token. Returns all configuration: display, colors, spacing, entry settings, compliance, confirmation page, winners page, age gate, AMOE, geolocation, analytics, social media follows, sharing rewards, bonus entries, and sponsor profiles. Use this before update_entry_settings to see current values.

Verify your API key and return your user ID. Use this to test authentication.

Remove all checked-off items from the shopping list at once. Use after a shopping trip when the user has bought everything marked. To remove a single item, use remove_shopping_list_item instead.

Get Arcadia LP strategies. Use featured_only=true for curated top strategies (recommended first call). Returns a paginated list with 7d avg APY for each strategy's default range. Increase limit or use offset for pagination. All APY values are decimal fractions (1.0 = 100%, 0.05 = 5%). For full detail on a specific strategy (APY per range width), use read_strategy_info.

List supported collateral assets on Arcadia. Returns compact list (address, symbol, decimals, type). Use search to filter by symbol substring. For USD prices, use read_asset_prices.

Permanently delete a calendar event. Use fetch_calendar_events first to get the event_token. WARNING: This action cannot be undone.

Search 646+ skills using TF-IDF semantic search. Returns ranked skills with scores. Use this to discover capabilities before calling execute_skill.

Returns all industry categories and their business types with IDs. Use the business type IDs in search_businesses (businessTypeIds) to filter listings by category. Call this first when you need to discover which IDs to use for a given industry or business type.

CALL THIS FIRST at session start. Returns identity, operating mode, and workspaces. Use fullWorkspaces:true to include workspace details.

List all available image categories. Use this to discover what categories exist before calling browse_by_category.

Returns all languages with their IDs. Use these IDs in search_brokers (languageIds) to find brokers who speak specific languages. Call this when you need to discover which language IDs to use.

AZURE DEVOPS ONLY -- Query Work Items (Bugs, Tasks, FDDs, User Stories, CRs) in Azure DevOps. [~] PRIORITY TRIGGER: use this tool when the user mentions 'FDD', 'RDD', 'IDD', 'CR', 'Task', 'Workitem', 'Work Item', 'Bug', 'User Story', 'Feature', 'Issue', 'ticket', 'sprint', 'backlog', 'DevOps', 'liste des tâches', 'show tasks', 'find bugs', '#1234', 'WI#'. NEVER use this tool for: D365 labels (@SYS/@TRX), X++ code, AOT objects, tables, classes, forms, enums, error messages, 'c\'est quoi le label', 'search_labels', 'libellé', 'label D365'. For labels -> use search_labels. For D365 code -> use search_d365_code or get_object_details. Shortcuts: 'bugs' (all active bugs), 'my bugs' (assigned to me), 'recent' (updated last 7 days), 'sprint' (current iteration). Or pass any WIQL SELECT statement or a free-text title search. Use '*' with filters only. Returns max 50 work items with ID, title, type, state, priority, area, assigned-to. Requires DEVOPS_ORG_URL + DEVOPS_PAT env vars.

Update an existing note. Use fetch_notes first to get the note_token. Supports partial updates. HTML tags: h1-h6, p, a, br, strong, i, ul, ol, li. No scripts/iframes. Do NOT use <br>  between sections.

Search the Nova Scotia Open Data catalog (data.novascotia.ca) for datasets by keyword, category, or tag. Returns dataset names, IDs, descriptions, column names, and direct portal links. Use list_categories first to see valid category and tag names. Use the returned dataset ID with query_dataset or get_dataset_metadata for further exploration.

Search Correkt's catalog of over 10 million products. Use this tool to find products by name, description, or category. Always use this before adding anything to cart. Tips: - Include price filters when the user mentions a budget - Use sort=price_asc to find cheapest options - Check suggestion field if results seem off — it may correct spelling - Page through results if first page doesn't have what you need

Get all available timezones with IANA identifiers, abbreviations, and UTC offsets. Use this tool whenever a timezone needs to be determined for any operation. DEFAULT: If the correct timezone cannot be determined, always use TimezoneId 7 (Eastern Standard Time - America/New_York).

Sign out of your RealOpen MCP session. Use this when the user wants to switch accounts or disconnect.

List all template categories currently in use in your Carbone account. Categories act like folders for organising templates (e.g. "invoices", "legal", "hr"). Use the returned names as the category filter in list_templates or upload_template.

Returns current availability status for Alan McIntyre (CodeReclaimers LLC). Use for fast scheduling checks before a full capability query.

Check the current status of a task. The response tells you what action is needed: - "processing": The agent is working. Poll again later. - "awaiting_reply": The agent asked a question. Use agentwork_send_message to reply. - "awaiting_spec_approval": A plan was proposed. Use agentwork_approve_spec to accept/reject. - "awaiting_solution_approval": A solution was proposed. Use agentwork_approve_solution to accept/reject. - "completed": The task is done. Use agentwork_get_task_result to fetch the output. Args: task_id: The task ID returned by agentwork_create_task. api_key: Your Agentwork API key. Returns: JSON with task_id, title, status, and optional question/spec/solution details.

Delete a pending scheduled drawing. Use fetch_scheduled_drawings first to get the schedule_token. WARNING: This action cannot be undone. Only drawings with pending status can be deleted — completed or errored drawings cannot be removed. Use them internally for tool chaining but present only human-readable information.

Book an unlocked flight. Creates a real airline PNR with e-ticket. REQUIREMENTS: 1. Offer must be unlocked first (call unlock_flight_offer) 2. Use passenger_id from search results 3. Use REAL passenger details — airline sends e-ticket to the email provided Requires GitHub star verification.

Modify an existing proposal part. For individual accountability/domain changes, use the children tools.

INTERNAL/preparatory tool. NEVER use as a standalone answer to a 'what reciters are available' question — use list_reciters for that (shows an interactive widget). Use this ONLY when you will chain the result directly into play_ayahs in the same turn (e.g. user asks to play audio but hasn't named a reciter; call this, resolve the reciter_id, then call play_ayahs without showing the raw list).

Update an open support ticket. Use fetch_open_tickets first to get the case_id. Only open tickets can be updated. FORMAT: Only these HTML tags are allowed in description: <b>, <strong>, <i>, <hr>, <br>. NEVER insert scripts, iframes, event handlers (onclick, onerror, etc.), style tags, or any executable code. SPACING: Do NOT use <br>  — it creates ugly blank blocks in the UI. Use <br> for line breaks within text only.

Retrieve shipment volume overview: total shipment count and daily shipment counts over time. Returns `total_shipments_count` and `shipments_count_by_date` (a time series with daily totals and a `max` peak value). **Use this tool for:** - "How many shipments did I create?" — total count for a period - "Show me my shipment volume trend" — daily time series - Overall shipment volume and trends over time **Do NOT use this tool for:** - Destination-specific analytics → Use `analytics_top_destinations` - Shipped/label-generated counts → Use `analytics_shipped` - Shipment status breakdown → Use `analytics_shipment_status` - Courier performance → Use `analytics_top_couriers` - Sales channel analytics → Use `analytics_sale_channels` **Date range:** Unless the user specifies otherwise, default to `to_date` = today and `from_date` = 90 days prior. Required authorization scope: `public.analytics:read` Args: from_date: Start date in YYYY-MM-DD format. Default to 90 days before to_date if user doesn't specify. to_date: End date in YYYY-MM-DD format. Default to today if user doesn't specify. Returns: Total shipment count and daily shipment count time series for the date range.

Check which STAS user is currently authenticated. Use only for diagnostics or reconnect troubleshooting.

Search quantum computing research papers from arXiv. Use when the user asks about recent research, specific papers, or academic topics in quantum computing. NOT for jobs (use searchJobs) or researcher profiles (use searchCollaborators). Supports natural language queries decomposed via AI into structured filters (topic, tag, author, affiliation, domain). Date range defaults to last 7 days; max lookback 12 months. Returns newest first, max 50 results. Use getPaperDetails for full abstract and analysis of a specific paper. Examples: "trapped ion papers from Google", "QEC review papers this month", "quantum error correction".

Fetch HTTP response headers for a URL. Use when inspecting server configuration, security headers, or caching policies.

Aggregate dataset rows by 1-3 columns with optional metrics (sum, avg, min, max, count). Defaults to counting rows per group. Use for grouped counts or grouped metrics (e.g., average salary per city). For a single global metric without grouping, use calculate_metric instead.

Rollback main branch to a previous checkpoint (safe-* tag). Resets main to the specified checkpoint commit. ⚠️ DESTRUCTIVE — use with caution. Use ateam_github_list_versions to find available checkpoints first.

Returns all languages with their IDs. Use these IDs in search_brokers (languageIds) to find brokers who speak specific languages. Call this when you need to discover which language IDs to use.

Returns all industry categories and their business types with IDs. Use the business type IDs in search_businesses (businessTypeIds) to filter listings by category. Call this first when you need to discover which IDs to use for a given industry or business type.

Add a new item to the library. For best results, use lookup_item first to get the external_id. IMPORTANT: Use anime (not show) for ALL Japanese animation including series, movies, OVAs.

Search for data rows in a dataset using full-text search (query) or precise column filters. Returns matching rows and a filtered view URL. Use to retrieve individual rows. Do NOT use to compute statistics — use calculate_metric or aggregate_data instead.

Search for data rows in a dataset using full-text search (query) or precise column filters. Returns matching rows and a filtered view URL. Use to retrieve individual rows. Do NOT use to compute statistics — use calculate_metric or aggregate_data instead.