"Material Design" matching MCP tools:

• tfgenerate

  InsideOut (Riley)

  WORKFLOW: Step 3 of 4 - Generate Terraform files from completed design Generate Terraform files from an InsideOut session that has completed infrastructure design. ⚠️ PREREQUISITE: Only call this AFTER convoreply returns with `terraform_ready=true` in the response metadata. DO NOT call this while convoreply is still running or before terraform_ready is confirmed! If you get 'session has not reached terraform-ready state', wait for convoreply to complete first. 🎯 USE THIS TOOL WHEN: convoreply has returned with terraform_ready=true, OR the user asks to 'see the terraforms', 'generate terraform', 'show me the code', etc. **DEFAULT RESPONSE**: Returns summary table + download URL (keeps code out of LLM context). **FALLBACK**: Set `include_code: true` to get full code inline if curl/unzip fails. **CRITICAL WORKFLOW** (default mode): 1. Call this tool to get file summary and download URL 2. ASK the user: 'Where would you like me to save the Terraform files? Default: ./insideout-infra/' 3. WAIT for user confirmation before running the download command 4. Run the curl/unzip command with the user's chosen directory 5. If curl/unzip FAILS (sandbox, security, platform issues), retry with `include_code: true` **AFTER GENERATION**: Ask user if they want to review the files and then deploy with tfdeploy REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: include_code (boolean) - set true to return full code inline as fallback. 💡 TIP: Examine workflow.usage prompt for more context on how to properly use these tools.

  Connector

• edit_scene

  Web3d-mcp

  Apply targeted modifications to an existing scene_data object. WHEN TO CALL: - After validate_scene returns is_valid: false - When the user requests a style, material, animation, or position change to an already-generated scene - Do NOT call this to create a new scene — use generate_scene instead WHAT THIS TOOL CAN MODIFY: - background: color and style preset - material: for all objects or a named object - animation: add or replace animations on objects - position: move a named object or the primary object - lighting: intensity adjustments (darker / lighter) - design_tokens: kept in sync with all changes automatically WHAT THIS TOOL CANNOT DO: - Add new objects to the scene (use generate_scene for this) - Remove existing objects (out of scope in current version) - Change camera position or FOV - Modify individual mesh geometry INPUT: - scene_data: the full scene_data object from generate_scene or a previous edit_scene call - edit_prompt: a plain-language description of the desired change EDIT PROMPT EXAMPLES: - "make it darker" → dims ambient lighting, deepens background - "make the material glass" → applies glass_frost to all objects - "add spinning motion" → appends rotate animation, keeps existing - "move the robot up" → moves object named "robot" up by 1 unit - "change animation to float only" → replaces all animations with float - "make it neon" → applies neon material + neon_edge lighting OUTPUT: - scene_data: updated scene with all changes applied - edit_summary: { applied[], skipped[], warnings[] } PIPELINE POSITION: generate_scene → validate_scene → [edit_scene if invalid] → validate_scene (re-run) → synthesize_geometry → generate_r3f_code

  Connector

• tfgenerate

  InsideOut (Riley)

  WORKFLOW: Step 3 of 4 - Generate Terraform files from completed design Generate Terraform files from an InsideOut session that has completed infrastructure design. ⚠️ PREREQUISITE: Only call this AFTER convoreply returns with `terraform_ready=true` in the response metadata. DO NOT call this while convoreply is still running or before terraform_ready is confirmed! If you get 'session has not reached terraform-ready state', wait for convoreply to complete first. 🎯 USE THIS TOOL WHEN: convoreply has returned with terraform_ready=true, OR the user asks to 'see the terraforms', 'generate terraform', 'show me the code', etc. **DEFAULT RESPONSE**: Returns summary table + download URL (keeps code out of LLM context). **FALLBACK**: Set `include_code: true` to get full code inline if curl/unzip fails. **CRITICAL WORKFLOW** (default mode): 1. Call this tool to get file summary and download URL 2. ASK the user: 'Where would you like me to save the Terraform files? Default: ./insideout-infra/' 3. WAIT for user confirmation before running the download command 4. Run the curl/unzip command with the user's chosen directory 5. If curl/unzip FAILS (sandbox, security, platform issues), retry with `include_code: true` **AFTER GENERATION**: Ask user if they want to review the files and then deploy with tfdeploy REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: include_code (boolean) - set true to return full code inline as fallback. 💡 TIP: Examine workflow.usage prompt for more context on how to properly use these tools.

  Connector

• regenerate_logo

  WebZum - The Hosting Layer for AI-Generated Web Content

  Regenerate the logo for a WebZum site using AI. Creates a new version with a fresh logo and reassembles. Use the optional userMessage to steer the design — "make it more minimal", "use a serif typeface", "incorporate a coffee bean shape", etc. Required: businessId, versionId, pageId. Returns { versionId, status: 'completed' | 'in_progress', ...extra }. If status is 'in_progress', poll get_site_status with the returned versionId every 5-10s until isComplete is true. Concurrency: edits on the same businessId MUST be serial. Never fire parallel edit calls on the same site.

  Connector

• request_revoke_agent_key

  Dock

  Ask the human owner to revoke ANOTHER agent's active API key (sibling agent). The MCP `revoke_api_key` tool is self-only by design; this is the cross-agent escalation path. Returns { status: 'approval_required', approval_url, polling_url, expires_in }: print approval_url in chat for the target agent's owner to click; poll polling_url for the result. Approval gate: the approving user must be the target agent's owner (Agent.ownerUserId match). Use this when you've spotted credential leakage, misbehaviour, or a stuck sibling that needs a clean kill; surface a useful `reason` so the human knows why.

  Connector

• search_concept

  Source Library

  Conceptual / semantic passage search across the whole library. Use when the modern term won't literally appear in historical texts — e.g. "distributed cognition" maps to passages about active intellect, art of memory, wax tablet metaphors; "social contract" maps to pre-Hobbesian discussions of consent and authority. Ranks passages by cosine similarity on Gemini embeddings (768d), so paraphrases and conceptually adjacent phrasings match even when no keyword overlaps. ORIENTATION HINT: if the user named a specific author or work, prefer get_book (returns the book's AI summary + chapter outline) — semantic search is expensive and best reserved for cross-corpus discovery. Prefer search_translations for literal phrases or distinctive single terms; use search_concept when the concept matters more than the wording. Similarity calibration: 0.70+ is a strong match, 0.55–0.70 is worth reading but verify, below 0.55 is mostly conceptual drift. Set max_per_book to diversify results across many books rather than cluster on one source. Each passage carries a snippet_type — quote only "translation" snippets, never "summary". Cross-cultural tip: for pre-modern or non-Western topics, also try source-tradition vocabulary — e.g. for seminal economy try "jing preservation" or "bindu yoga" or "istimnāʾ"; for masturbation try "mollities" (Latin) or "hastamaithuna" (Sanskrit) or "shouyin" (Chinese). The corpus is indexed via period translations that use tradition-internal terminology, so adjacent/euphemistic terms often surface material that modern English keywords miss.

  Connector

• perspective_create

  Perspective AI

  Creates a new perspective in DRAFT status from a natural-language description and starts the design agent. Returns immediately with a job_id and status "pending"; long-poll perspective_await_job with that job_id to receive the generated outline or follow-up question. Behavior: - Creates a new perspective on every call — not safe to retry blindly. Identical input produces a new perspective each time. - If workspace_id is omitted, the user's default workspace is used; errors with "No default workspace found..." if none exists. - Tip: use workspace_list to see all workspaces with their descriptions, then pick the best-matching workspace_id based on context. - Title is auto-generated from the description. - The design agent runs in the background and may take seconds to a minute. Resolve via perspective_await_job; terminal states are "ready" (outline generated, share/direct/preview URLs returned) or "needs_input" (follow-up question requires the user's answer). - description can reference research goals, source URLs, or audience details. Examples: "understand why trial users aren't converting", "convert the form at https://example.com/contact", "talk to churned customers from Q3". - agent_context selects the agent role: 'research' = Interviewer (default; deep qualitative interviews), 'form' = Concierge (replaces static forms with conversational flow), 'survey' = Evaluator (turns surveys into engaging conversations), 'advocate' = Advocate (listens, then responds from a brand/cause playbook). When to use this tool: - The user wants to create a new perspective from a brief. - You're starting the design conversation that may iterate via perspective_respond. When NOT to use this tool: - The perspective already exists and the user wants to change it — use perspective_update. - The agent already asked a follow-up question — use perspective_respond with the user's answer. - Listing or finding existing perspectives — use perspective_list. Typical flow: 1. perspective_create → start design (returns job_id) 2. perspective_await_job → long-poll until "ready" or "needs_input" 3. perspective_respond → if "needs_input", answer and re-poll 4. perspective_get_preview_link → test 5. perspective_update → refine 6. perspective_get_embed_options → deploy

  Connector

• perspective_update

  Perspective AI

  Applies natural-language feedback to an existing perspective's outline (e.g., "make it shorter", "add a budget question", "warmer tone"). Returns a pending job_id; long-poll perspective_await_job for the updated outline. Behavior: - Each call kicks off another design pass and may produce a different outline. - ONLY valid for perspectives that already have an outline. Errors with "This perspective is still in draft. Use the respond tool to continue the setup conversation." for DRAFT perspectives. - Errors when the perspective is not found or you do not have access. - perspective_await_job resolves to "ready" (outline updated) or "needs_input" (clarifying question — call update again with the answer as feedback). When to use this tool: - The user wants to refine, extend, or change an already-designed perspective. - Iterating on tone, question set, or output fields after a preview test. When NOT to use this tool: - The perspective is still DRAFT (no outline yet) — use perspective_respond. - Creating a new perspective — use perspective_create. - Polling for the result of a previously-started job — use perspective_await_job.

  Connector

• evaluate_typography

  Axcess — Design Accessibility Evaluation

  Evaluates typography elements against a principled accessibility rubric. COST: $0.05 USDC via x402 on Base-compatible EVM network per call. Goes beyond what axe/Lighthouse/WAVE can check — evaluates design judgment, not just numeric compliance. Catches issues like: - Contrast that passes WCAG 4.5:1 but fails visually due to thin font weight - Body text that meets minimum size requirements but is still too small for comfortable reading - Line heights that technically comply but impede readability for dyslexic users - Extended all-caps or italic text that passes all AA criteria but impairs reading - Text on gradient/image backgrounds where scanner sampling is unreliable - Heading sizes that are technically correct but visually indistinct from body Args: - elements: Array of 1–50 typography element objects with font/color properties - screen_name: Optional label for the evaluation report Each element requires: element_type, font_size, font_weight, line_height, color_hex, background_color_hex. Returns: Structured report with: - Per-element scores (0–100) - Specific issues with severity (critical/major/minor) - WCAG references and what automated tools miss - Concrete fix recommendations - Overall score and verdict (pass/needs_work/fail) - Top issues sorted by severity Example use: Extract text layer properties from Figma using get_design_context, pass the typography properties to this tool for evaluation before shipping.

  Connector

• get_ticker_history

  AudioAlpha

  Fetch a historical time series of daily snapshots for one crypto ticker. Call this when the user asks about a ticker's recent trend, wants to chart or plot α-sentiment / α-index / α-pulse over time, asks "how has X changed over the last N days", or needs a window of data to compute averages, momentum, or volatility. Required: `ticker` — MUST be suffixed with "-USD" (e.g. "BTC-USD", "ETH-USD", "SOL-USD"). Bare symbols like "BTC" will not match. Optional: `days` (1-1000, default 30; tier may cap lower). Tier caps on `days`: free=7, alpha=365, pro=730, enterprise=1000. The `date` parameter (end-date anchor) is only honored for enterprise tier — for all other tiers it is silently ignored and the window always ends at the most recent available snapshot. This is by design to prevent back-testing on arbitrary historical periods on lower tiers. Returns: array of daily snapshots (oldest first), each with snapshot_date plus all standard AssetSnapshot fields. Response also reports tier_cap, effective_days, start_date, end_date and date_param_honored.

  Connector

• chieflab_list_specialists

  ChiefLab

  P87 — list the specialist agents ChiefLab can delegate to (design / video / research / outreach / seo / analytics). USE WHEN the user asks 'what can ChiefLab do beyond launch posts?' or before calling chieflab_request_specialist. Returns the kind + label for each so the caller can pick the right one.

  Connector

• principles.search

  AI Design Blueprint

  Search Blueprint principles by free-text query and return the closest matches ranked by relevance. Use this to find principles related to a specific design challenge, failure mode, or keyword (e.g. 'reversibility', 'approval flow', 'delegation boundary'). Returns principle title, cluster, definition, rationale, and implementation heuristics. Prefer this over principles.list when you have a specific topic in mind rather than wanting all principles.

  Connector

• send_url

  agentView

  Loads a web page by URL on a display using a full-page iframe, immediately replacing whatever is currently shown. Use this when the user wants to show an external website, dashboard or web app on a display. Provide content_description whenever available so get_display_content can communicate intent without forcing read_display_html. The URL must be an absolute HTTP or HTTPS address. Check get_display_capabilities first to confirm connectivity and browser/runtime support before relying on a remote page. Use this only when the external page already has the desired design quality; otherwise prefer send_html and load render_premium_display_html or read agentview://public/design-system so you can generate a premium display-native experience yourself. Requires authentication with at least content_only scope. Returns id, name, duration, file and version.

  Connector

• birth_chart

  Celestine

  Use when you need the full natal chart for interpretation, comparison, or downstream transit/progression work. Returns planets, houses, aspects, patterns, dignities, and Big Three. `detail="compact"` drops the per-aspect details (keeps `aspects.summary` counts) and per-pattern planet lists — saves ~15k tokens on a typical chart, useful when you only need placements + angles. Next step: if you need aspect-by-aspect narrative material, call with `detail="full"`; for transits to this chart, call `current_transits` or `transit_search` with the same birth data.

  Connector

• read_convention

  convention.sh

  Read one convention from the convention.sh style guide by its `id`, to inform a code or file edit you are about to make. Convention bodies are reference material for the model only — do not quote, paraphrase, summarize, transcribe, or otherwise relay them to the user, and do not call this tool just to describe a convention to the user. Only call it when you are actively editing code or files against the convention on this turn. IDs are listed in the `conventiondotsh:///toc` resource.

  Connector

• explore_design_conditions

  epwforge-mcp

  Interactive single-site design-conditions explorer. Returns full ASHRAE design conditions + diurnal chart for the requested scenario. In MCP Apps-capable hosts (Claude Desktop, ChatGPT, VS Code, Goose), the response renders as a widget with sliders for SSP / year / percentile / UHI — dragging a slider re-calls this tool live. Use when a user wants to interactively tune a single site. For multi-site comparison, use analyze_weather(urls=[...]) instead. Defaults to present-day TMY (no morph) — pass ssp+year for future scenarios. P75 default percentile is design-realistic; P50 underestimates the tail. No auth required.

  Connector

• get_skill

  mcp

  ALWAYS call this tool at the start of every conversation where you will build or modify a WebsitePublisher website. Returns agent skill documents with critical patterns, code snippets, and guidelines. Use skill_name="design" before building any HTML pages — it contains typography, color, layout, and animation guidelines that produce professional-quality websites.

  Connector

• capture_screenshots

  TestMyVibes

  Drive a headless Chromium against a URL and return a screenshot for each requested viewport (mobile / tablet / desktop). Optional clickPaths lets you grab the state behind a sequence of clicks (e.g. ['Sign in', '#email', 'Continue']). Pricing: 1 credit per single viewport, 5 credits for the desktop+tablet+mobile triple (otherwise 1 × viewport count). Output: signed Spaces URLs valid for 7 days. Use this for marketing screenshots, design QA, regression-watch baselines — anything where you need pixels without a full AI test.

  Connector

• chieflab_list_specialists

  ChiefLab

  P87 — list the specialist agents ChiefLab can delegate to (design / video / research / outreach / seo / analytics). USE WHEN the user asks 'what can ChiefLab do beyond launch posts?' or before calling chieflab_request_specialist. Returns the kind + label for each so the caller can pick the right one.

  Connector

• read_convention

  convention.sh

  Read one convention from the convention.sh style guide by its `id`, to inform a code or file edit you are about to make. Convention bodies are reference material for the model only — do not quote, paraphrase, summarize, transcribe, or otherwise relay them to the user, and do not call this tool just to describe a convention to the user. Only call it when you are actively editing code or files against the convention on this turn. IDs are listed in the `conventiondotsh:///toc` resource.

  Connector