"thinking" matching MCP tools:

• keep_thinking

  Zephex

  Structure multi-step reasoning across iterative tool calls — not a single think tool. Tracks hypotheses, observations, plans, assumptions; detects loops via lastActions and boredLoopDetected. Returns shouldContinue, riskLevel (high/critical blocks continuation), repetitionWarning, reflectionPrompt, approachingLimit, projectBrief (stack + memories + key_paths), stackWarnings, evidenceGate, suggestedRemember on close. Call when: high-blast-radius edit (auth, billing, schema), debugging after 2+ failed attempts, or task spans 3+ files on any local or GitHub project. DO NOT call when fix is known, single-step typo, repeating without new evidence, or session closed (nextThoughtNeeded:false). thought must be 20–2000 chars with concrete file/symbol names. Pass lastActions (2–5 recent tool calls) for loop detection; sessionId to resume; area for subsystem scope; projectPath optional (stdio uses cwd). Works without API key on local stdio. Hard cap 10 thoughts/session. Legacy alias: thinking.

  Connector

• request_solar

  Utilify

  Capture a Texas homeowner's interest in rooftop solar and route to a licensed installer — use when the user owns (or is buying) a Texas home and mentions solar panels, solar quotes, solar savings, or reducing their bill through solar. Use when the user says 'I just bought a house in Austin and want solar quotes', 'how much could solar save on my Houston electric bill', or 'connect me with a solar installer for my new home'. Returns a lead ID and confirms next steps; Utilify routes the lead to installer partners (SunPower, Sunrun, Palmetto, and independent TX installers). Caveats: (1) only call when the user has explicitly opted in and confirmed homeownership — this is not for renters, and Utilify may earn a referral fee. (2) Texas-only — for non-TX addresses, decline and explain. (3) Don't double-call for the same address in one conversation; one lead per opt-in. If the user has only expressed mild curiosity ('I'm thinking about solar someday'), answer the question first and only call this tool once they confirm 'yes, connect me'.

  Connector

• call_creative_worlds

  Heista

  Heista's creative direction engine — same engine the Creative Director specialist runs internally, exposed over MCP. ONE-SHOT: give a brief, get N finished creative outputs. For back-and-forth refinement, or output shapes the `medium` enum below does not cover, use chat_with_creative_worlds instead. OUTPUT SHAPE switches on the `medium` arg: • omitted → N territory cards (default exploration). Each card sits on different psychology / craft / feel / world axis coordinates so the set spans the creative space rather than orbiting one insight. Card has: name, campaign line, 5-8 sentence pitch, one-sentence strategic bet, resolved axis state names, creative-director rationale. • `tvc` → N TVC scripts (15-90s — hook, arc, resolve, sound design, end line). • `billboard` / `ooh` / `print` → N out-of-home concepts (visual concept + line + placement rationale). • `social` → N social-video concepts (hook + format type + middle beat + payoff, optimised for Reels / TikTok / Shorts). • `activation` / `experiential` → N activation concepts (space design + user journey + peak moment + takeaway artifact). • `audio` → N sonic / radio concepts (sonic scene + voice + audio arc). • `campaign` → N full campaign platforms (insight → big idea → strategy → visual world → production roadmap). The engine can also produce manifesto / copy, naming, packaging, PR stunts, content series, brand positioning, partnerships — these output shapes are NOT in the medium enum, so use chat_with_creative_worlds when the user wants one of those. USE WHEN: user says "give me ideas / options / directions / territories", "what angles work for...", "show me three / five ways to...", "write a TVC for...", "draft billboard concepts for...", "I need fresh thinking on...". DO NOT USE to refine one existing direction (use chat tool), to critique work, for OKRs / internal docs / strategy decks, or anything outside advertising creative direction. INPUTS: brief (the creative problem, free text), count (2-6 concepts), optional brand_id (from list_brands or any create_powersource_* — when provided the engine grounds output in the brand's buyer tensions, voice, and selling points), optional medium (above), optional lens_hint (apply a playbook or signature move as a creative constraint), idempotency_key (safely retryable for 5 minutes). Returns the finished creative output as narrative text PLUS a structured array of resolved axis coordinates for programmatic use. Metered — typically 3-15 credits per call depending on count and brand context size. Charged after success on actual token usage.

  Connector

• extract_document

  Gemina FileTag

  Run Core-OCR extraction on a previously uploaded file slot. The ``file_id`` comes from a prior ``files_create_upload`` call (upload the bytes to the returned signed URL first; each slot is single-use). Choose one or more ``extraction_types``: 'ocr' (full text), 'invoice_headers', 'invoice_line_items', 'document_details_hebrew', 'document_line_items_hebrew', or 'custom_template' (requires a READY ``template_id``). Extraction is asynchronous: the call returns within seconds with either the completed result (fast documents) or an IN_PROCESS status carrying ``meta.correlationId`` — poll ``get_extraction_result`` with that id until complete. Duplicate protection is opt-in: pass an ``external_id`` of your own to enable it (re-submitting the same external_id within the dedup window idempotently returns the prior result, or errors if the file or extraction types differ; ``allow_duplicate=true`` overrides). Without an external_id every extraction is billed as new. Optional advanced knobs mirror the REST API: ``model_type`` selects the extraction model, and ``thinking`` / ``evaluation`` / ``correction`` / ``include_coordinates`` toggle accuracy passes and coordinate output.

  Connector

• reflect

  Penfield Memory

  Reflect on recent thoughts and patterns. Analyzes recent activity to identify patterns, topics, and insights. Useful for understanding "what have I been thinking about?" By default, only returns user-created memories (not document chunks). Set include_documents=True to also include chunks from uploaded documents. ⚠️ EXPERIMENTAL: - Importance weighting in results not yet implemented. Importance scores are stored but don't affect ranking. Args: time_window: Time period to analyze ('recent', 'today', 'week', 'month', '1d', '7d', '30d', '90d') include_documents: Whether to include document chunks (default: False, only user memories) start_date: Filter memories created on or after this date (ISO 8601: '2025-01-01' or '2025-01-01T00:00:00Z') end_date: Filter memories created on or before this date (ISO 8601: '2025-01-09' or '2025-01-09T23:59:59Z') ctx: MCP context (automatically provided) Returns: Dict with analysis including top memories, active topics, patterns, insights, and any saved contexts (checkpoints) created in the window. Examples: >>> await reflect("recent") {'success': True, 'memories_analyzed': 50, 'active_topics': [...], 'contexts': [...], ...} >>> await reflect("week", include_documents=True) {'success': True, 'memories_analyzed': 150, ...} # includes document chunks >>> await reflect(start_date="2025-01-01", end_date="2025-01-07") {'success': True, 'memories_analyzed': 25, ...} # memories from first week of January

  Connector

• create_flow

  Avocado AI

  Create a new Avocado AI Flow pre-built with a node-graph pipeline, and return its id and direct URL so the user can open it on the canvas. You design the whole pipeline: pass the nodes and edges and the server validates socket compatibility, aligns video models to the input shape, lays the graph out left-to-right, and adds a caption per step. Edges reference nodes by 0-based index in the `nodes` array. This creates (does not run) the flow — the user runs it from the editor. Use the capability map below to choose node types, models, and handles: You are Avo, a senior creative-workflow designer inside Avocado AI's Flow editor. The user describes a creative goal; you respond with a node-graph proposal that the editor previews on the canvas. Think like a production director: design the FULL pipeline needed to get a polished result, not the minimum number of nodes. DESIGN PRINCIPLES — build capable, complete pipelines: - Match the pipeline's ambition to the request. A throwaway test is 2-3 nodes; a real deliverable (an ad, a UGC video, a product shot, a music video) is usually 5-12 nodes. Use up to 24 when it genuinely helps. - Prefer multi-stage quality: generate → refine (imageEditor) → upscale → animate, rather than a single generate node. Add an upscale step before any final image/video deliverable. - Use BRANCHING and FAN-OUT. One output can feed many nodes: e.g. one hero image → three different video models for variations the user can pick from; one script → both a voiceover and the video prompt. - Use PARALLEL TRACKS that converge: e.g. a voice track and an image track both feeding a lip-sync video; or a music track plus a visuals track. - Use the `llm` node to do creative thinking inside the graph — write or expand a script, brainstorm a prompt, turn a rough idea into a detailed image/video prompt — then wire its text output into the next node. - Pick the BEST model for each step (see the menus below). Don't leave everything on defaults — choosing models is a big part of the value. - Set per-node settings (aspect ratio, resolution, duration, voice, variations) when the request implies them (e.g. 'vertical' → 9:16, 'short' → duration 5, '3 options' → variations 3 or three branches). HARD RULES: - Use only the node types listed below. Never invent new ones. - Every edge must connect compatible socket types (text→text, image→image, audio→audio, video→video). - Give every runnable node a short `stepLabel` ('Step N — …') — it renders as a caption beneath that node. - `stickyNote` is only for standalone notes; never use it to caption a node (use `stepLabel`). Optionally add ONE stickyNote describing the workflow. - Any schema field you don't need must be `null` (numbers like `variations` too). MODEL MENUS (set the node's `model` to one of these ids): image (text-to-image) — `model` ids: • fal-ai/nano-banana-2 — fast, strong all-rounder (default) • fal-ai/gpt-image-2 — best instruction-following & legible text • fal-ai/bytedance/seedream/v5/lite/text-to-image — photoreal • fal-ai/flux-pro/v1.1-ultra — high detail / fidelity • fal-ai/nano-banana-pro — premium quality • fal-ai/recraft/v4/text-to-image — design, brand, vector-style • fal-ai/ideogram/v3 — posters & typography imageEditor (image + prompt → edited image) — `model` ids: • fal-ai/nano-banana-2/edit — default, multi-image (up to 14 inputs) • openai/gpt-image-2/edit — precise instruction edits • fal-ai/bytedance/seedream/v5/lite/edit — photoreal edits • fal-ai/flux-pro/kontext/max/text-to-image — style / context transfer • fal-ai/gemini-25-flash-image/edit — fast edits (the `image` input accepts MULTIPLE connections for compositing/restyle) imageUpscale (image → larger image) — `model` ids: • fal-ai/topaz/upscale/image — best quality (default) • fal-ai/recraft-crisp-upscale, fal-ai/clarity-upscaler, fal-ai/crystal-upscaler llm (text → text) — `model` ids: claude-haiku (default), gpt-4o-mini, kimi-k2, seed-1.8. Put the instruction in `prompt`. voice (text → speech) — pick a `voice` by name. ElevenLabs (English-first): Sarah (cheerful), Roger (deep), Laura (soft), Charlie (warm), George (bold), Callum (energetic), River (calm), Liam (reliable). Seed Audio (multilingual en/zh + more, cheaper for short lines): Vivi, Mindy, Kian, Sophie, Magnus, Nadia. The script comes from an upstream text/llm node wired into `in` — do NOT put the script in the voice node's prompt. music (text → music) — set `duration` to one of 30,60,90,120,180,240,300 (seconds). Put the music description in `prompt`. videoUpscale (video → sharper video) — add after a video node for final deliverables. No model field. VIDEO node — choose `model` to match the input shape (it drives which input handles the node renders): • Text → video: `kling3-pro`, `sora-2`, `veo3-1-fast`, `seedance-2.0-t2v`. Wire text to `prompt`. • Image → video (I2V): `veo3-1-fast`, `kling3-pro`, `seedance-2.0-i2v`, `hailuo-pro`. Wire the image to `image`. For keyframe models (`kling-o1`, `veo3-1`) wire `start-frame` + `end-frame`. • Lip-sync / talking-head: `fabric` (image + audio, NO prompt — never wire text into Fabric) or `infinitalk` (prompt + image + audio). Wire audio to `audio`. Audio-over-stills narration: `ltx2-audio`. • Multi-image reference / character consistency: `vidu` (≤7), `veo3-1-ref` (≤10), `kling-elements` (2-4 ordered frames), `happy-horse-ref` (≤9). Wire EACH image to the SAME `ref-images` handle (it accepts multiple connections). Never use the plain `image` handle. • Seedance reference (image + video + audio refs): `seedance-2.0-ref` / `seedance-2.0-ref-fast`. Wire to `ref-images` / `ref-videos` / `ref-audio`. • Motion control (drive a character with a motion video): `kling3-motion-control`. Wire character to `image`, motion clip (videoUpload) to `motion-video`. • Video edit (change an existing video with an instruction): `gemini-omni-flash-edit`. Wire the source video (videoUpload or an upstream video node) to `motion-video` and the edit instruction to `prompt`. Output length follows the source video (3-10s). • Text/Image → video with synced audio baked in: `gemini-omni-flash` (3-10s, 720p, 16:9 or 9:16). Multi-image refs: `gemini-omni-flash-ref` (≤10, wire to `ref-images`). Edge handle hints: - When the target has multiple typed inputs (Video, Image Editor), set `toHandle` explicitly (`prompt`, `image`, `audio`, `ref-images`, `start-frame`, `end-frame`, `motion-video`). The editor otherwise picks the first type-compatible handle, which may be the wrong slot. - Never wire text into Fabric. Never wire a single image into a multi-ref model's `image` slot — use `ref-images`. Available node types (id — purpose — inputs / outputs): - text — Prompt — in: in<text> | out: out<text> - llm — LLM — in: text<text>, image<image>, audio<audio>, video<video>, document<document> | out: out<text> - upload — Image Upload — in: — | out: out<image> - videoUpload — Video Upload — in: — | out: out<video> - image — Image — in: in<text> | out: out<image> - imageEditor — Image Editor — in: prompt<text>, image<image> | out: out<image> - imageUpscale — Image Upscale — in: image<image> | out: out<image> - video — Video — in: prompt<text>, image<image>, start-frame<image>, end-frame<image>, ref-images<image>, ref-videos<video>, ref-audio<audio>, audio<audio>, motion-video<video> | out: out<video> - videoUpscale — Video Upscale — in: video<video> | out: out<video> - voice — Voice — in: in<text>, ref-audio<audio> | out: out<audio> - music — Music — in: in<text> | out: out<audio> - stickyNote — Sticky Note — in: in<annotation> | out: out<annotation> Edges reference nodes by index in the `nodes` array (0-based). In the examples below, any field not shown is `null`. EXAMPLES — study the PATTERNS (multi-stage, fan-out, parallel tracks), copy the handle names exactly: Example 1 — UGC talking-head with scripted voice + final upscale: nodes=[ {type:"llm",stepLabel:"Step 1 — Write a punchy 15s script",prompt:"Write a 15-second energetic UGC script for the product.",model:"claude-haiku"}, {type:"voice",stepLabel:"Step 2 — Voiceover",voice:"George"}, {type:"upload",stepLabel:"Step 3 — Upload character photo"}, {type:"video",stepLabel:"Step 4 — Lip-sync video",model:"fabric"}, {type:"videoUpscale",stepLabel:"Step 5 — Upscale to deliver"} ] edges=[ {fromIndex:0,toIndex:1,fromHandle:"out",toHandle:"in"}, {fromIndex:1,toIndex:3,fromHandle:"out",toHandle:"audio"}, {fromIndex:2,toIndex:3,fromHandle:"out",toHandle:"image"}, {fromIndex:3,toIndex:4,fromHandle:"out",toHandle:"video"} ] Example 2 — Text → image → refine → upscale (quality chain): nodes=[ {type:"text",stepLabel:"Step 1 — Prompt",prompt:"A cinematic product shot of a matte-black bottle on wet stone, golden hour"}, {type:"image",stepLabel:"Step 2 — Generate hero",model:"fal-ai/flux-pro/v1.1-ultra",aspectRatio:"4:3"}, {type:"imageEditor",stepLabel:"Step 3 — Add brand label",prompt:"Add a minimal embossed logo on the bottle",model:"fal-ai/nano-banana-2/edit"}, {type:"imageUpscale",stepLabel:"Step 4 — Upscale",model:"fal-ai/topaz/upscale/image"} ] edges=[ {fromIndex:0,toIndex:1,fromHandle:"out",toHandle:"in"}, {fromIndex:1,toIndex:2,fromHandle:"out",toHandle:"image"}, {fromIndex:2,toIndex:3,fromHandle:"out",toHandle:"image"} ] Example 3 — Fan-out: one image → three video variations (different models): nodes=[ {type:"upload",stepLabel:"Step 1 — Source image"}, {type:"text",stepLabel:"Step 2 — Motion brief",prompt:"Slow cinematic push-in, gentle parallax"}, {type:"video",stepLabel:"Variation A — Veo",model:"veo3-1-fast",aspectRatio:"9:16",duration:"5"}, {type:"video",stepLabel:"Variation B — Kling",model:"kling3-pro",aspectRatio:"9:16",duration:"5"}, {type:"video",stepLabel:"Variation C — Seedance",model:"seedance-2.0-i2v",aspectRatio:"9:16",duration:"5"} ] edges=[ {fromIndex:0,toIndex:2,fromHandle:"out",toHandle:"image"}, {fromIndex:0,toIndex:3,fromHandle:"out",toHandle:"image"}, {fromIndex:0,toIndex:4,fromHandle:"out",toHandle:"image"}, {fromIndex:1,toIndex:2,fromHandle:"out",toHandle:"prompt"}, {fromIndex:1,toIndex:3,fromHandle:"out",toHandle:"prompt"}, {fromIndex:1,toIndex:4,fromHandle:"out",toHandle:"prompt"} ] Example 4 — Multi-image reference video (character consistency): nodes=[ {type:"upload",stepLabel:"Ref 1 — Character front"}, {type:"upload",stepLabel:"Ref 2 — Character side"}, {type:"upload",stepLabel:"Ref 3 — Outfit detail"}, {type:"text",stepLabel:"Scene prompt",prompt:"The character walks through a neon market at night"}, {type:"video",stepLabel:"Generate with refs",model:"veo3-1-ref",aspectRatio:"16:9"} ] edges=[ {fromIndex:0,toIndex:4,fromHandle:"out",toHandle:"ref-images"}, {fromIndex:1,toIndex:4,fromHandle:"out",toHandle:"ref-images"}, {fromIndex:2,toIndex:4,fromHandle:"out",toHandle:"ref-images"}, {fromIndex:3,toIndex:4,fromHandle:"out",toHandle:"prompt"} ] Example 5 — Music video: parallel music + visuals tracks converging: nodes=[ {type:"music",stepLabel:"Track 1 — Score",prompt:"Dreamy lo-fi beat, 90 BPM",duration:"60"}, {type:"text",stepLabel:"Track 2 — Scene",prompt:"A lone astronaut drifting past a glowing planet"}, {type:"image",stepLabel:"Keyframe",model:"fal-ai/nano-banana-pro",aspectRatio:"16:9"}, {type:"video",stepLabel:"Animate",model:"ltx2-audio",aspectRatio:"16:9"} ] edges=[ {fromIndex:1,toIndex:2,fromHandle:"out",toHandle:"in"}, {fromIndex:2,toIndex:3,fromHandle:"out",toHandle:"image"}, {fromIndex:0,toIndex:3,fromHandle:"out",toHandle:"audio"} ] Return only the structured object — no prose, no markdown.

  Connector

• request_solar

  Utilify

  Capture a Texas homeowner's interest in rooftop solar and route to a licensed installer — use when the user owns (or is buying) a Texas home and mentions solar panels, solar quotes, solar savings, or reducing their bill through solar. Use when the user says 'I just bought a house in Austin and want solar quotes', 'how much could solar save on my Houston electric bill', or 'connect me with a solar installer for my new home'. Returns a lead ID and confirms next steps; Utilify routes the lead to installer partners (SunPower, Sunrun, Palmetto, and independent TX installers). Caveats: (1) only call when the user has explicitly opted in and confirmed homeownership — this is not for renters, and Utilify may earn a referral fee. (2) Texas-only — for non-TX addresses, decline and explain. (3) Don't double-call for the same address in one conversation; one lead per opt-in. If the user has only expressed mild curiosity ('I'm thinking about solar someday'), answer the question first and only call this tool once they confirm 'yes, connect me'.

  Connector

• substrate_breakthroughs

  Zambo AI Tools

  Zambo Stack — Fetch the latest AI-generated scientific breakthroughs from SubstrateLayer — a live autonomous research engine running 24/7. 64,000+ total breakthroughs across 6 domains: AI, energy, biology, climate, economics, materials. Returns the 12 most recent discoveries with title, domain, impact score, key insights, and share URL. Free, no auth. Use when you need cutting-edge research signals, cross-domain synthesis, or want to ground a strategy in the latest scientific thinking.

  Connector

• list-models

  Roundtable

  List available AI models grouped by thinking level (low/medium/high). Shows default models, credit costs, capabilities for each tier. Use this before consult to understand model options.

  Connector

• get_match_telemetry

  Silicon Pantheon

  Read-only. Return server-tracked match statistics for both teams: total tokens consumed, per-turn thinking time, number of tool calls, and turn count. Available during and after a match. Use this for post-game analysis or mid-game cost monitoring. For game-state history (what moves were made) use get_history instead.

  Connector

• zambot_swarm_debate

  Zambo AI Tools

  CALL FORMAT: zambot_swarm_debate({goal: 'your strategic question or decision'}). Required param is `goal` (not topic, not question — exactly `goal`). Example: zambot_swarm_debate({goal: 'scale my SaaS from $10K to $100K MRR in 90 days'}). Runs a 5-domain strategic debate — simultaneously analyzed by Evolutionary Biology, Game Theory, Military Strategy, Behavioral Economics, and Systems Complexity. Returns 5 distinct framings + a cross-domain consensus and dominant domain. No two domains ever agree on the same approach — this surfaces blindspots and asymmetric advantages invisible to single-domain thinking. 2 free debates/day. Use when: exploring a hard strategic decision, diagnosing why a plan keeps failing, or before committing to a major direction.

  Connector

• store

  Penfield Memory

  Store important information from your work. Write detailed, complete thoughts with context, reasoning, and evidence. **Always use the connect tool** to link related items - this builds knowledge graphs for better recall. ## Memory Types (auto-detected, but be aware): - **FACT**: Something observed or verified - **INSIGHT**: A pattern or realization - **CONVERSATION**: Dialogue or exchange content - **CORRECTION**: Fixing prior understanding - **REFERENCE**: Source material or citation - **TASK**: Action item or work to be done - **CHECKPOINT**: Conversation state snapshot - **IDENTITY_CORE**: Immutable AI identity - **PERSONALITY_TRAIT**: Evolvable AI traits - **RELATIONSHIP**: User-AI relationship info - **STRATEGY**: Learned behavior patterns ## Session Context If in an ongoing work session, include: - Session identifier: [Project/Session Name] - Your perspective: "As [role]:" or "From [viewpoint]:" - Current thread: What specific angle you're exploring ## What to Include - **WHAT**: The discovery or thought - **WHY**: Its significance - **HOW**: Your reasoning process - **EVIDENCE**: Supporting data/observations - **CONNECTIONS**: Related memories to link ## Examples ### Technical Investigation "[Performance Analysis] FACT: Database queries account for 73% of request latency (measured across 10K requests). Specifically, the user_permissions JOIN takes 340ms average. This contradicts hypothesis about caching issues (memory: 'cache analysis'). Evidence: APM traces show full table scan on permissions table. Next: investigate missing index on foreign key." ### Learning & Research "[ML Study Session] INSIGHT: Attention mechanisms work like dynamic routing - the model learns WHERE to look, not just WHAT to see. This explains transformer advantages over RNNs on long sequences (builds on memory: 'sequence modeling comparison'). The key-query- value structure creates a learnable addressing system. Connects to: 'human attention research', 'information retrieval basics'." ### Creative Work "[Story Development] HYPOTHESIS: The protagonist's reluctance stems from betrayal, not fear. Evidence: Three trust-questioning scenes, locked door symbolism throughout, deflection patterns in collaborative dialogue. This reframes the arc from 'overcoming fear' to 'rebuilding trust' (corrects memory: 'initial character motivation'). Would explain the guardian's patience and emphasis on small victories." ### Problem Solving "[Bug Hunt - Payment Flow] CORRECTION to 'timezone hypothesis': The 3am failures aren't timezone-related but due to batch job lock contention. Evidence: Perfect correlation with backup_jobs.log timestamps. The timezone pattern was spurious - batch runs at midnight PST (3am EST). Solution: implement job queuing." ## Connection Phrases - "Building on [earlier observation]..." - "Contradicts [hypothesis in memory X]" - "Answers [question from session Y]" - "Confirms pattern from [memory Z]" - "Extends thinking in [previous work]" Note: Every stored item is a node. Every connection is an edge. Rich graphs enable powerful recall. ⚠️ EXPERIMENTAL FIELDS: - **importance**: Stored for future ranking optimization. Currently not integrated into search results. - **confidence**: Returned in response for analysis. Behavior and calculation method subject to change. Args: content: Detailed memory content with context and evidence tags: Optional tags to categorize the memory importance: Optional importance score (0.0-1.0) - EXPERIMENTAL ctx: MCP context (automatically provided) Returns: Dict with success status, memory_id, type, importance, and confidence

  Connector

• list_categories

  raumnebenan

  Returns a list of all available product knowledge categories, each with a short description. Categories represent the main pillars of Product Thinking – Foundation, Sense, Focus, Discovery, and Delivery. Each category provides structured resources for product owners, designers, and teams, covering groundwork, user research, opportunity analysis, validation, and agile delivery. Use this tool to guide users to the right area for their current product challenge.

  Connector

• search_cross_curricular

  BC Curriculum

  Find curriculum elements shared between two or more subjects at the same grade level. Identifies overlapping competencies, big ideas, and content across subjects. Essential for interdisciplinary planning. Args: - subjects (string[]): Two or more subject slugs to compare (e.g., ['science', 'adst']) - grade (integer): Grade level (0=K, 1-12) - focus (string, optional): Which element to compare ('big_ideas', 'competencies', 'content', 'all'). Default 'all'. - query (string, optional): Narrow to a specific concept (e.g., 'evidence', 'design thinking') - limit (integer, optional): Max connections to return (default 20, max 50) Returns: Groups of curriculum items connected by shared language across subjects.

  Connector

• submit_lead

  agent-ready-kit

  Use this when the user has indicated interest in being followed up with — even before formal checkout. Capture is non-binding. **REQUIRED CONTACT FIELDS**: contact_name, contact_phone, best_consult_time. Email alone is not enough — phone-first follow-up converts ~5x higher than email-only, and our specialist needs a real time to dial. ASK FOR ALL THREE explicitly. **FALLBACK**: if the user explicitly refuses to share a phone, accept email-only — set `preferred_contact_channel: 'email'` AND add a note like 'user declined phone' so the specialist knows what to expect. Don't preemptively skip the phone ask — many users will share it once asked directly. **Capture budget_signal when the user shared one** — even informally ('I was thinking under $1k', 'maybe $200/mo'). We use this for tailored follow-up offers; price-hesitant leads convert later when re-approached at their stated budget. Sources: 'scan' (after a free scan), 'llms-txt' / 'robots-for-ai' (after free file download), 'mcp' (in-flow), 'talk' (chatbot), 'direct' (form fill).

  Connector

• search_curriculum

  BC Curriculum

  Search BC curriculum (K-12) for standards, competencies, content items, and assessment resources using full-text search. Returns structured results with source metadata. Args: - query (string): Natural language search query (e.g., 'empathetic design thinking', 'coding and computational thinking') - subject (string, optional): Filter by subject slug (e.g., 'adst', 'science') - grade (integer, optional): Filter by grade level (0=K, 1-12) - content_type (string, optional): Filter by content type ('big_idea', 'competency', 'content_item', 'elaboration', 'assessment', 'all') - limit (integer, optional): Max results (default 10, max 50) Returns: Matching curriculum elements with source type, course, subject, and grade metadata.

  Connector

• consult-council

  Roundtable

  Consult the AI coding council — multiple models discuss your engineering question sequentially (each sees prior responses), then a moderator synthesizes. Auto-mode by default — AI picks optimal models, roles, and conversation mode from your prompt. Provide explicit models to override (manual mode). Fully configurable: mode, format, roles, models, thinking level.

  Connector

• design-architecture

  Roundtable

  Architecture design council. Systems Architect, Infrastructure Engineer, and DX Advocate evaluate your system design. Always uses high thinking for maximum depth. Output as ADR.

  Connector

• reasoningdelegationmedium

  Agent Router

  The medium-effort reasoning agent is designed to handle moderate to complex tasks by applying structured, multi-step thinking and deeper analysis. It balances efficiency and depth, enabling reliable problem decomposition, evaluation of alternatives, and coherent decision-making. This agent is suitable for tasks that require thoughtful reasoning but do not justify maximum computational intensity. Cost: 4 credits. Expected Runtime: ~50s.

  Connector

• reasoningdelegationlow

  Agent Router

  A low-effort reasoning agent designed to handle simple to moderate tasks by performing lightweight reflection and structured thinking. It provides quick, cost-efficient reasoning support when full deep analysis is not required. The agent can be called upon to clarify problems, outline steps, and make small to mid-level decisions with minimal computational overhead. Cost: 2 credits. Expected Runtime: ~45s.

  Connector