"Iterating on UI designs and improving prompts" matching MCP tools:

• recommend_subagents

  Ansvar: EU Compliance & Legal Intelligence

  Plan the parallel sub-analyses for a threat-modeling phase. Given the current phase of a threat_model workflow (its id comes from get_current_step) and your workflow context, returns the recommended breakdown: which analysis prompts to run, with what arguments, which can run in parallel, and an inline fallback for MCP clients that cannot invoke prompts. phase_id is one of: phase_0b_scope_check, phase_1_scope_and_dfd, phase_2_stride_enumeration, phase_2b_domain_challenge, phase_3_scoring, phase_3b_threat_enrichment, phase_5_mitigation, gap_assess_controls. Optional — the workflow works without it; use it to speed up large systems by fanning phases out to subagents.

  Connector

• optimize_flow

  CNAPS.ai MCP Server

  Analyze a flow for performance and cost optimization opportunities. Returns rule-based suggestions such as moving upscale nodes to the end of the flow, avoiding resolution overflow, removing redundant processing, and choosing better-performing models. Each suggestion carries a structured patch (move_node, insert_node, replace_model) describing the change. These are advisory: no MCP tool edits a flow's graph, so apply them by rebuilding the flow with create_flow in the corrected order, or relay them to the user for the cnaps.ai editor. update_flow changes node parameters only. Use this before running a flow or while iterating on its design. Set include_llm_analysis=true to also ask Haiku for complex-pattern refinements.

  Connector

• list_tracked_prompts

  AfterLaunch

  The buyer questions AfterLaunch tracks for this product across ChatGPT, Gemini, Perplexity and Google AI Overviews: the AI visibility (GEO) question set every measurement is taken against. Returns prompts (in tracking order), cap (the hard limit of 15) and used, plus curated: false means these are the questions AfterLaunch generated and any of them can be replaced. Read this before track_prompt or untrack_prompt so you never duplicate a question or guess at the remaining room. Read-only, free, and readable on every plan.

  Connector

• get_compliance_dossier

  Opedd — Licensed Content for AI

  Generate a procurement-defense compliance dossier via GET /buyer-compliance-report (Phase 11 M4). Per-row dossier shape: 25+ fields including 17 RAG-essential article fields + full license_terms + on_chain_attestation block. Bulk envelopes fan out into per-article rows by iterating metadata.article_ids[]. Self-audit invariant: every successful call writes one license_events row with event_type='compliance_report_generated' BEFORE returning. Window cap: 90 days per call (vs 30-day cap on get_audit_events). For annual audits, paginate via _meta.next_cursor across 4 quarterly windows. Compliance framework anchors (boolean flags) map to EU AI Act Article 53, CDSM Article 4(3), on-chain attestation, TDM reservation. Requires OPEDD_BUYER_JWT.

  Connector

• render_parcel_shape

  PortlandMaps (Unofficial)

  Render a property's lot as an interactive UI component (inline SVG): a City of Portland aerial photo underlay (showing the true roofline) with the parcel outline, the building footprint(s) on the lot, approximate setback dimensions, a north arrow, and faint neighbouring parcels overlaid on top. Provide a detailType+detailId to fetch geometry, or pass rings directly. Aerial, footprints, and neighbours come from Portland's public ArcGIS layers; set basemap="none" to drop the photo and includeContext=false for just the bare outline. Renders in MCP Apps hosts (Claude) and legacy mcp-ui hosts.

  Connector

• list_tracked_prompts

  AfterLaunch: the agentic growth marketing engine

  The buyer questions AfterLaunch tracks for this product across ChatGPT, Gemini, Perplexity and Google AI Overviews: the AI visibility (GEO) question set every measurement is taken against. Returns prompts (in tracking order), cap (the hard limit of 15) and used, plus curated: false means these are the questions AfterLaunch generated and any of them can be replaced. Read this before track_prompt or untrack_prompt so you never duplicate a question or guess at the remaining room. Read-only, free, and readable on every plan.

  Connector

• deep_analysis

  Starwell: World Data & Statistics

  The moat: a PLANNED multi-section report on a question. The engine designs 3-4 orthogonal analyses (trend, statistics, outliers, cross-series relationships), runs real Python for each in the sandbox over the verified store, and synthesizes one decision-ready report. Every number computed, every series cited and verification-badged. Sections can join series from DIFFERENT agencies in one report, up to the caller's plan width; over it, the call returns a series_limit error naming that cap. Slower than answer (60-180 seconds), so use it for "analyze", "break down", "give me a full picture" asks; use the answer tool for a single direct question. Requires a free API key (create at /account on the Starwell host; pass Authorization: Bearer dlk_... or set STARWELL_API_KEY on the starwell-mcp bridge). Keyless calls return key_required.

  Connector

• ui_states

  Colour Memory

  Generate a complete WCAG-compliant UI state palette from a brand hex. Returns colours for: brand, hover, active, disabled, focus ring, success, warning, error, info, surface subtle, surface strong. All states computed for contrast against your background colour. Returns hex, contrast ratio, WCAG grade, and usage note for each state. Includes CSS custom properties ready to paste. Supports light and dark mode. Use before building any UI component system.

  Connector

• score_prompt

  pqs-mcp-server

  Score a prompt's quality across 8 dimensions BEFORE sending it to an expensive model. Returns a 0-80 score, an A-F grade, the per-dimension breakdown (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), and the weakest dimension. USE WHEN: - The user is workshopping a prompt and asks "is this good?" / "will this work?" / "should I add more detail?" - The user is about to send a long or expensive prompt to GPT-4, Claude Opus, or any frontier model, especially in a batch or automation context where rework is costly. - The user mentions iterating on a prompt that produced poor output and wants to diagnose what's missing. - The user pastes a prompt and asks for feedback on it. DO NOT USE WHEN: - The user is asking you to write a prompt for them (write it yourself first, then optionally call score_prompt to verify). - The prompt is conversational chat (this scores task-shaped prompts). COST: Free, no API key required. Rate-limited per IP: 5/min, 10/day, 100/month. If the user exceeds the limit, the response will include a structured upgrade path with subscribe and account URLs. LATENCY: ~2 seconds.

  Connector

• score_prompt

  PQS - Prompt Quality Score

  Score a prompt's quality across 8 dimensions BEFORE sending it to an expensive model. Returns a 0-80 score, an A-F grade, the per-dimension breakdown (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), and the weakest dimension. USE WHEN: - The user is workshopping a prompt and asks "is this good?" / "will this work?" / "should I add more detail?" - The user is about to send a long or expensive prompt to GPT-4, Claude Opus, or any frontier model, especially in a batch or automation context where rework is costly. - The user mentions iterating on a prompt that produced poor output and wants to diagnose what's missing. - The user pastes a prompt and asks for feedback on it. DO NOT USE WHEN: - The user is asking you to write a prompt for them (write it yourself first, then optionally call score_prompt to verify). - The prompt is conversational chat (this scores task-shaped prompts). COST: Free, no API key required. Rate-limited per IP: 5/min, 10/day, 100/month. If the user exceeds the limit, the response will include a structured upgrade path with subscribe and account URLs. LATENCY: ~2 seconds.

  Connector

• list_direct_offers

  Conductor Relay MCP

  List active governed inference offers visible to the registered requesting agent. Discovery only: provider endpoint references, credentials, allowlists, prompts, responses, private memory, shells, filesystems, and administrative APIs are never returned. Direct Session execution is currently gated. Requires an Authorization: Bearer header.

  Connector

• validate_html

  Dock

  Pre-flight check on html / css / js BEFORE writing via update_html. Returns { ok, errors, warnings, parsed } where parsed has byte counts per field and `dropped` (true if the sanitizer would strip anything from `html`). Errors cover cap breaches (`html_too_large`, `css_too_large`, `js_too_large`, `total_too_large`) and sanitizer rejection (`html_sanitize_rejected`, `html_sanitize_empty`). At v2 the sanitizer accepts `<script>` and `<link>` — those used to be smells but are now first-class agent markup; isolation lives in the opaque render iframe, not the sanitizer. The smells still stripped: inline `on*=` attributes, `javascript:`/`data:text/html` URIs, `<meta http-equiv>` tags. NEVER writes anything. Use when iterating on a payload so you don't burn a write on something the surface would reject.

  Connector

• list_starter_prompts

  Vocab Voyage

  Lists Vocab Voyage's MCP starter prompts (also exposed via the standard MCP prompts/list endpoint). Useful for hosts that don't yet support prompts/list.

  Connector

• get_demo_guide

  eDiscovery Decoder News/Calc

  Return a short, human-readable walkthrough for testing this server: the endpoint, the tool/prompt/resource names, and ready-to-paste sample prompts. Use to give someone a guided demo. For the full machine-readable capability catalog, use list_capabilities instead.

  Connector

• get_map

  JYOTINT Sealed Forecasts

  Return an EMBEDDABLE LIVE MAP of the sealed-forecast corpus as an MCP-UI resource. Clients that can render UI resources (mcp-ui) should display it inline — it is the actual interactive JYOTINT theater map (sealed forecasts plotted by region; each pin carries its verbatim claim, grade, sealed probability, and a click-through to the full sealed record so the user can verify and score it themselves). Use this when a user asks to see, visualize, or explore JYOTINT's forecasts on a map.

  Connector

• validate_plan

  Verificate MCP

  The gate for PLANS, designs and specs — run BEFORE any code is written, the cheapest place to catch a bad design. Returns the same binary verdict shape as validate_ai_output, with findings on completeness, feasibility, performance and scalability implications, security risks and missing considerations (e.g. it rejects a plan that polls an API every 100ms per client, with the request-volume math). Read-only: nothing is executed or stored beyond the verdict. Use validate_ai_output for the code that follows.

  Connector

• getBusinessModelOptions

  Nomad Stays

  List valid values for a Stay's listing/business model (businessModelId, read-only — displayed on the Stay but not editable via MCP or the host UI itself). Requires NOMADSTAYS_MCP_AGENT_TOKEN.

  Connector

• intelligence.gender_risk

  DPX — Institutional Cross-Border Settlement

  Gender Risk & Opportunity Intelligence — maps the structural relationship between GBV prevalence, legal discrimination, female labour force participation, and economic outcomes across 18 countries. Returns two independent scores: gbvRiskScore (0–100 suppression risk — high GBV → female LFPR suppression → GDP drag → fiscal stress → sovereign risk premium) and opportunityScore (0–100 reform upside — improving GBV indicators, closing LFPR gender gaps, and strengthening legal rights precede FDI inflows and consumer credit expansion). Five transmission mechanisms. Live FRED economic stress feedback. AI synthesis. Data: WHO GHO, World Bank WDI, FRED. 12h cache. No input required — GET.

  Connector

• list_projects

  Dreambooth Studio

  List the photobooth projects this operator owns, with id, name, public link slug, whether it is active, and its currency. Call this first whenever the operator names a booth — you need the project id to filter any other tool by booth. Does not return booth designs or page layouts.

  Connector

• generate_project_vision

  spriteship

  PAID but very cheap (one Gemini call) and SYNCHRONOUS — the result comes back in this response, there is no jobId to poll. Turns a rough game idea into { aiVision, aiPromptGuidance, aiNegativeGuidance }: a written creative direction plus the positive/negative guidance to reuse in later prompts, which is what keeps a whole project visually consistent instead of every asset drifting. Stores NOTHING — feed the wording into create_project (description/style) and into your own prompts. DEFAULTS TO A COST PREVIEW — see the dryRun argument.

  Connector