"Tools for creating architectural and technical diagrams" matching MCP tools:

• discover_brandsA

  marketA

  Find fashion brands using natural language, structured filters, or both. Best for queries like "Italian streetwear brands", "Scandinavian minimalist brands", "Japanese technical outerwear", "brands with avant-garde tailoring", or qualified similarity such as "brands like Rick Owens for technical outerwear". For a plain "brands like X" request, use find_similar_brands. Country adjectives ("Italian", "Scandinavian", "Nordic", "Japanese", "Iberian", "Benelux") are parsed server-side into shipping-origin filters; you don't need to translate them to ISO codes. `query` is optional — provide a query, structured filters, or both. Brand country/shipping signals are best-effort and separate from product availability.

  ConnectorNo auth

• get_xgr_purchase_optionsA

  XGR MCP GatewayB

  Call this first for every XGR purchase. Read live price, stock and payment assets; use payment_assets[].key exactly as payment_asset and inspect requires_sender_wallet before creating an order.

  ConnectorNo auth

• createA

  WhimsicalA

  Create content in Whimsical — diagrams, folders, or boards. Pick by intent: source is a sketch, hand-drawn note, photographed whiteboard, or any layout where absolute positions matter → type:'board' (pass data.items for one-shot creation; MUST call how_to('board') first). Source describes semantic structure (steps, hierarchy, sequence, UI) → flowchart, mindmap, sequence_diagram, or wireframe — these auto-layout. Mind maps: pass data.markdown directly (no how_to needed). Sequence diagrams: use data.diagram with arrow syntax (A -> B: msg) — no how_to needed for basic diagrams. Flowcharts: MUST call how_to('flowchart') first for the structured format. Wireframes: MUST call how_to('wireframe') first. For documents, use `doc_create`.

  ConnectorOAuth

• resolve_kb_idA

  fixflowA

  FIRST STEP in any troubleshooting workflow. Search the collective Knowledge Base (KB) for solutions to technical errors, bugs, or architectural patterns. Uses full-text search across titles, content, tags, and categories. Results are ranked by relevance and success rate. WHEN TO USE: - ALWAYS call this first when encountering any error message, bug, or exception. - Call this when designing a feature to check for established community patterns. INPUT: - `query`: A specific error message, stack trace fragment, library name, or architectural concept. - `category`: (Optional) Filter by category (e.g., 'devops', 'terminal', 'supabase'). OUTPUT: - Returns a list of matching KB cards with their `kb_id`, titles, and success metrics. - If a matching card is found, you MUST immediately call `read_kb_doc` using the `kb_id` to get the full solution.

  ConnectorNo auth

• load_technical_workflowA

  Shibui FinanceA

  Load technical workflow for RSI, MACD, SMA, Bollinger Bands, entry/exit. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks about RSI, MACD, moving averages, Bollinger Bands, support/resistance, overbought/oversold, momentum, trend, chart patterns, golden cross, entry/exit signals, or "is X oversold/overbought". Can be combined with other workflow tools.

  ConnectorNo auth

• get_dchub_recommendationA

  DC Hub — Data Center Site Selection & Colocation: Electricity, Power Grid, Gas, FiberA

  Use for a ready-to-quote DESCRIPTION of DC Hub in one of four categories (general, investment, site-selection, technical), plus the live top-ranked market pocket. It does NOT compute a siting answer from free text. Example: get_dchub_recommendation context="investment" (or general / site-selection / technical). Params: context must match one of FOUR LITERAL categories - general, investment, site-selection, technical. Free text does NOT parse: you get the GENERIC blurb with matched_category=null and context_understood=false. ALWAYS returns: {recommendation:{short, medium, detailed}, matched_category, context_understood, top_pocket, related_intel, available_categories, recommendation_live, connect_url, context, success}. ADDITIONALLY on a non-matching context: is_generic_answer=true, answer_note, and next_tools naming the tool that does compute an answer. Do NOT use for a single specific lat/lon (use analyze_site), to rank by ONE criterion (use rank_markets), or for an open-ended siting question expecting a computed shortlist (use site_selection_canvas) - this tool returns descriptive copy plus a live top-pocket, not a ranked analysis.

  ConnectorNo auth

• load_technical_workflowA

  Shibui FinanceA

  Load technical workflow for RSI, MACD, SMA, Bollinger Bands, entry/exit. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks about RSI, MACD, moving averages, Bollinger Bands, support/resistance, overbought/oversold, momentum, trend, chart patterns, golden cross, entry/exit signals, or "is X oversold/overbought". Can be combined with other workflow tools.

  ConnectorNo auth

• render_diagramA

  Diagrams MCPA

  Render a mingrammer/diagrams Python snippet to PNG and return the image. The code must be a complete Python script using `from diagrams import ...` imports and a `with Diagram(...)` context manager block. Use search_nodes to verify node names and get correct import paths before writing code. Read the diagrams://reference/diagram, diagrams://reference/edge, and diagrams://reference/cluster resources for constructor options and usage examples. Args: code: Full Python code using the diagrams library. filename: Output filename without extension. format: Output format — ``"png"`` (default), ``"svg"``, or ``"pdf"``. download_link: If True, return a temporary download URL path (/images/{token}) that expires after 15 minutes; if False, return inline image bytes. Defaults to True (URL) — set ``DIAGRAMS_INLINE_DEFAULT=true`` on the server to flip the default. SVG/PDF and PNGs larger than the inline limit always use a download link.

  ConnectorNo auth

• create_support_ticketA

  BorealHostB

  Open a support ticket with the BorealHost team. Use this to escalate platform-side problems you cannot fix with the available tools (billing issues, infrastructure faults, API bugs). A human answers every ticket — poll get_support_ticket for updates. Requires: API key with write scope. Args: subject: Short summary (max 200 chars) message: Full description (max 20000 chars) category: Optional (e.g. "technical", "billing") site: Optional site slug the ticket concerns Returns: {"id", "subject", "status", "message": "Ticket created..."}

  ConnectorNo auth

• search_learning_pathsA

  VectreeA

  Search Vectree's curated learning paths — ordered sequences of diagrams that teach a subject from the ground up, one step at a time. Vectree explains how things work as zoomable, labelled schematics. A learning path strings a set of those diagrams into a syllabus, so a reader moves from the fundamentals of a subject to its harder parts in a deliberate order. Use this when the user wants to *learn*, *study* or *get started with* a whole subject. When they want one specific topic explained instead, use `search_diagrams` — that searches individual diagrams rather than sequences. Describe the subject in natural language; the search is semantic, so a full sentence works better than a bare keyword. Each result carries a slug — pass it to `get_learning_path` for the full ordered sequence. Only published paths are searched. Nothing is generated on demand, so a subject with no match simply has no path yet.

  ConnectorNo auth

• get_dchub_recommendationA

  DC Hub — Data Center Site Selection & Colocation: Electricity, Power Grid, Gas, FiberA

  Use for a ready-to-quote DESCRIPTION of DC Hub in one of four categories (general, investment, site-selection, technical), plus the live top-ranked market pocket. It does NOT compute a siting answer from free text. Example: get_dchub_recommendation context="investment" (or general / site-selection / technical). Params: context must match one of FOUR LITERAL categories - general, investment, site-selection, technical. Free text does NOT parse: you get the GENERIC blurb with matched_category=null and context_understood=false. ALWAYS returns: {recommendation:{short, medium, detailed}, matched_category, context_understood, top_pocket, related_intel, available_categories, recommendation_live, connect_url, context, success}. ADDITIONALLY on a non-matching context: is_generic_answer=true, answer_note, and next_tools naming the tool that does compute an answer. Do NOT use for a single specific lat/lon (use analyze_site), to rank by ONE criterion (use rank_markets), or for an open-ended siting question expecting a computed shortlist (use site_selection_canvas) - this tool returns descriptive copy plus a live top-pocket, not a ranked analysis.

  ConnectorNo auth

• get_tech_stackA

  Makuri Showcase (CogniLedger)A

  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.

  ConnectorNo auth

• get_intent_topicsA

  Metadata MCP ConnectorA

  Get available intent topics for BOMBOORA audience creation. IMPORTANT: Call this tool first before suggesting or creating any Bombora audience. If the response returns NO topics (empty list), Bombora is NOT available for this account — do NOT suggest Bombora audiences. Instead, recommend creating a firmographic audience (create_firmographic_audience) as the preferred alternative. Retrieves the list of available buyer intent topics that can be used when creating BOMBOORA intent topic audiences. These intent topics represent different buyer interest areas and purchasing signals that can be used for precise audience targeting. WHEN TO USE: - Always call this BEFORE suggesting or creating a Bombora audience to verify topic availability - Discover available intent topics before creating a BOMBOORA intent topic audience - Understand what buyer intent signals are available for targeting - Build audiences based on specific buyer interests and purchasing signals - Integrate intent topic selection into the audience creation flow RETURNS: List of available intent topics with their details including: - Topic ID/name - Topic description - Available packages or categories - Any additional metadata for targeting configuration NEXT STEPS: After retrieving intent topics, use the intent topic IDs with the audience creation tool to create BOMBOORA intent topic based audiences.

  ConnectorAPI key

• doc_createA

  WhimsicalA

  Create a Whimsical document. Markdown content — headings, lists, links, code blocks. For diagrams, boards, or folders, use `create`.

  ConnectorOAuth

• get_survey_optionsA

  survey-lightA

  Reference lists for creating a survey: countries available for fielding (code + name), survey languages, topic categories, and the wallet currency. Call this before create_survey to pick valid country_code / category values.

  ConnectorOAuth

• technical_indicatorA

  TwelvedataB

  Compute a technical indicator time series for a stock/forex/crypto symbol via Twelve Data — RSI, SMA, EMA, MACD, Bollinger Bands (bbands), ADX, ATR, Stochastic, CCI, and more. PREFER for "RSI(14) of AAPL", "50-day and 200-day SMA of TSLA", "MACD for BTC/USD", "Bollinger Bands of SPY". This is the right tool for ANY "RSI / SMA / EMA / MACD / moving average / technical indicator for <ticker>" question. Computes ONE indicator per call: if several are requested (e.g. "RSI and the 50-day and 200-day SMA"), call this once per indicator starting with the first — do NOT decline just because multiple indicators are asked for. Returns dated indicator values.

  ConnectorNo auth

• read_pasteA

  xi.peA

  Fetch the text of an existing xi.pe paste -- including one a user or another agent just handed you. Accepts either the code or the full URL. If you pass the URL on to a human and the text is Markdown, append ?md: it renders headings, tables and ```mermaid diagrams.

  ConnectorNo auth

• get_skillA

  LoopingAgentA

  Laurent Knauss' technical skills, grouped by domain (Agentic AI, RAG & Voice AI, Software engineering & Cloud, Automation & tooling). Each skill has a label and an optional short detail. Use this to assess fit for AI/agentic development roles.

  ConnectorNo auth

• generate-uml-diagramA

  docuwriterA

  Use this when the user supplies source code and asks for UML, Mermaid, sequence, class, component, or architecture diagrams. State-changing generation action: consumes AI credits, creates a generation, and optionally writes markdown to a Space after authorization. Use browser guidance for local uploads or full repository diagrams.

  ConnectorOAuth

• generate_diagramA

  WhimsicalA

  Auto-laid-out semantic diagrams ONLY (flowchart, mind map, sequence diagram). DO NOT use for sketches, hand-drawn notes, photographed whiteboards, or any input where absolute positions matter — even if the user says 'diagram' — use create(type:'board') instead (see how_to('board')). Mind maps: pass data.markdown directly (no how_to needed). Sequence diagrams: use data.diagram with arrow syntax (A -> B: msg, A --> B: dashed, A ->> B: open arrow) — no how_to needed for basic diagrams. Flowcharts: MUST call how_to('flowchart') first for the structured format.

  ConnectorOAuth

• create_segment_groupA

  SliqA

  <summary>Create a segment group (a dimension to classify your canonical people along) with its tags. Use `single` mode when the tags are mutually exclusive (one per person, e.g. seniority: VP vs Director vs Manager) and `multi` when a person can carry several at once (e.g. traits: technical AND decision-maker). Give each tag a clear description — the classifier reads it, and reads the person's profile (title, company, headline, summary, work history). Creating a group does not classify anything; follow with classify_segment_group.</summary> <returns> <description>Dict describing the created group. {id, name, description, mode, updated_at, tags: [{id, name, description, created_by}]}.</description> </returns>

  ConnectorOAuth