"A task involving critical or creative thinking" matching MCP tools:

• whenpeak_best_window

  WhenPeak

  Find today's best time window for one kind of work, using the stored sleep history of the account this server is configured with. Returns a start and end time for the window and the projected capacity across it, tuned to the kind of work: analytical, creative, learning or administrative. Choose this tool when the user wants a slot for a task later today. Use whenpeak_performance_now for the current moment instead, and whenpeak_quick_predict when working from sleep the user describes rather than stored history. Requires WHENPEAK_API_KEY on the server and reads that one account's history, so it is only meaningful where the server runs with the user's own key. Without a key it returns a not_configured error rather than failing. Read-only and stores nothing, but each call counts against that account's monthly quota. Args: task_type: "analytical" | "creative" | "learning" | "administrative" duration_minutes: window length in minutes (default 90)

  Connector

• audit_dependency_tree

  Commit — Supply Chain Risk Scoring

  Map the full dependency tree of an npm package and identify CRITICAL supply chain risks at every level. Unlike auditing a flat list of packages, this tool traverses the dependency graph — showing not just your direct dependencies but also what your dependencies depend on. Hidden CRITICAL packages (sole publisher + >10M weekly downloads) often lurk 1-2 levels deep. Risk flags: - CRITICAL: single npm publisher + >10M weekly downloads — sole point of failure for a massive attack surface - HIGH: sole publisher + >1M/wk, OR new package (<1yr) with high adoption - WARN: no release in 12+ months (potential abandonware) depth=1 (default): root package + all direct dependencies depth=2: also traverses one more level for any CRITICAL/HIGH direct deps (reveals hidden exposure) Examples: - audit_dependency_tree("express") — see all of Express's deps and their risk scores - audit_dependency_tree("langchain", 2) — reveal transitive CRITICAL deps 2 levels deep - audit_dependency_tree("@anthropic-ai/sdk") — audit Anthropic SDK full tree Use this when someone asks: - "What am I really depending on?" - "Are my dependencies' dependencies safe?" - "Show me the full supply chain risk for package X"

  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

• score_creative

  Raven

  Score a creative prompt, script, or ad concept for hook strength, benefit clarity, product signal, call-to-action, channel fit, audience fit, and brand fit. This is a transparent heuristic, not a proprietary prediction model. Local brand profiles are not available on the hosted (remote) endpoint (per-user state is a later phase). Omit 'brand_profile_id' to score the pasted creative statelessly.

  Connector

• find_similar_creatives

  CreativeScope — Mobile Game Ad Creative Intelligence

  Find visually similar creatives using the stored vector of an existing creative. For a concept without an ID, query selects an explainable seed from available creative metadata and then uses the same vector-neighbor search. For an English concept, send the original English terms only. The service resolves Chinese source-label equivalents internally before selecting the seed. Returns creative records ordered from most to least visually similar; low-similarity and near-duplicate results are excluded, and raw similarity scores are not exposed. If request_echo.seed_basis identifies a proxy seed, clearly disclose that limitation instead of presenting the results as an exact concept match. Example: 'Show variants of the toilet run viral creative concept.'

  Connector

• submit_brief

  IBO Studio MCP

  Submit the creative brief for a PAID order: pass order_token (from get_order; session ids are not accepted here) plus project fields (product, goal, audience, channels, resolution, launch, links, constraints) and files[] from create_upload_url. Delivery resolution must be selected before creative kickoff. Customer identity comes from the verified payment. NOTE: unpaid/anonymous submissions are rejected here; for Custom Production inquiries without payment use the submit_custom_inquiry tool instead.

  Connector

• path_explorer

  cpp-cpm-engine

  Logic-trace driver-chain explorer — answers "WHY is this activity critical?" and "WHAT does it drive?". Traces driving predecessors backward from a target activity to project start (the "why critical" chain) and/or driving successors forward to project finish (the "what it drives" chain). Detects constraint-driven artificial criticality and cites AACE RP 49R-06 when found. Supports multiple parallel critical paths (MCPM) and near-critical paths. Use this tool when investigating a single activity's logic chain. For a project-wide CP / logic health audit, use ``critical_path_validator``. Args: xer_path: server-side path to the schedule XER. xer_content: full text of the schedule XER (alternative for hosted/remote use). Supply EXACTLY ONE of path/content. target_activity_codes: list of task_codes to trace; if empty, all CP / near-critical endpoints are traced. direction: 'backward' (predecessors), 'forward' (successors), or 'both' (default). include_near_critical: also trace near-critical endpoints (within float band). output_dir: optional dir for HTML / CSV / JSON outputs. Returns: { "paths": [{chain dicts ...}], "output_files": {dashboard, csv, json}, "project_finish": "YYYY-MM-DD", "project_name": ..., "data_date": ... }

  Connector

• keep_thinking

  Zephex

  Structure multi-step debugging and planning across tool calls — not a one-shot think. Tracks hypotheses, observations, plans; detects loops via lastActions; riskLevel high/critical blocks dangerous edits (drop table, prod deploy). Loads projectBrief (stack, key_paths, project_memory recall) on local project. On close, suggestedRemember → call project_memory remember. 4 credits hosted. Hard cap 10 thoughts/session. Call when: stuck after 2+ failed debug attempts, auth/billing/schema change spans 3+ files, flaky test you cannot explain, or you need a plan before editing. Pass lastActions (2–5 recent tool calls), goalAnchor after thought 2, sessionId to resume, area for subsystem. NOT when fix is known, single typo, repeating without new evidence, or session ended (nextThoughtNeeded:false). Read thoughtConfirmed and shouldContinue first. Legacy alias: thinking. Example: keep_thinking({ thought: 'Hypothesis: refresh token not rotated in middleware', thoughtType: 'hypothesis', thoughtNumber: 1, totalThoughts: 5, nextThoughtNeeded: true, confidence: 0.6, goalAnchor: 'Fix auth logout loop', lastActions: ['find_code(query=refreshToken)', 'read_code(target=authMiddleware)'], area: 'auth' }). Read-only.

  Connector

• get_session_dossiers

  VaultCrux Memory Core

  Retrieve pre-synthesized per-session memory dossiers (typed: experience | fact | preference; with When/Involving/To-purpose metadata). Use for multi-session or preference-style questions where stitching across conversations is the bottleneck — the dossier already summarises each session's key events. Two modes: mode='search' with a query (BM25-ish ranking over summary+purpose, optional type_filter), or mode='list' returns the tenant's most-recent dossiers chronologically. Tenants without FEATURE_SESSION_DOSSIERS enabled return an empty list (no error).

  Connector

• cancel_scheduled_task

  Valuein — SEC EDGAR Fundamentals & Smart-Money Data

  Cancel a pending scheduled task by id (from schedule_task or list_scheduled_tasks). Only a `pending` task can be cancelled — one that already woke (completed) cannot be un-woken. Idempotent: cancelling an already-cancelled task is a no-op. Tier: sp500+ (sample rejected).

  Connector

• search_official_docs

  404.directory

  Search current first-party OpenAI, Microsoft Learn, AWS, and Cloudflare documentation in one call. Use this as the default documentation research tool for questions involving any of those providers, especially comparisons or cross-cloud architecture. Select only relevant sources when the provider is known; omit sources to search all four in parallel. Returns each provider result separately with partial-failure reporting and provenance. No account or API key is required.

  Connector

• nevent_get_paid_ad_creative

  Nevent MCP

  Get the creative content of a specific ad: copy (body, title, description, CTA), click URL, UTM params, and pre-signed S3 image/video URLs (TTL ~1 hour). Use after nevent_list_paid_ads to get a valid adId. Null imageUrl/videoUrl means the asset mirror job has not run yet — retry in ~5 minutes. For Dynamic Creative Ads (hasDca: true), the dca field contains multiple creative variants. A 404 may mean this tenant is not enrolled in the insights pilot — call nevent_paid_ads_health to confirm.

  Connector

• create_gantt

  mcp-server

  Create a Gantt chart from a task list — no account or API key needed. YOU author the plan: list the tasks in execution order with realistic working-day durations and dependencies (0-based positions of earlier tasks; use { task, type, lag } for start-to-start/finish-to-finish links or lag). Milestones have duration 0. Only add a dependency where a task truly needs another one finished - independent tasks should run in PARALLEL (share a predecessor, or take no dependencies at all and start at the project start). Group tasks into top-level phases for a structured plan/WBS: the phase task gets isPhase: true, its tasks get parent = the position of the phase. LoopGantt schedules it with its critical-path engine and returns a picture of the chart, the dates, the critical path and a link where the user can view, export (PNG/PDF) and save the chart. Always show the user the link. Tasks with a due date take deadline: YYYY-MM-DD (a marker - the reply reports the fit). Use create_gantt when the user wants a chart to open, export or save; use schedule_project instead for what-if date math where nothing should be stored.

  Connector

• get_ad

  Spytrend

  Fetch a single ad by its id with FULL details including its creative media: the full ad TEXT in body (this is the only surface that serves it), body_chars (its length in UTF-8 characters), title, creative URL, geos, status, advertiser. body is absent when the ad genuinely has no text; body_chars is absent when the length could not be read — never read an absent field as zero. Media urls on media.spytrend.com are permanent; a media entry with expiring=true is the original signed Facebook CDN link of a not-yet-mirrored fresh ad — it dies within hours/days, NEVER put it into reports or exports (re-fetch the ad later for the permanent link). QUOTA: 1 token (this delivers the ad's creative media). With source=tiktok: 100 tokens (the TikTok row is the billable resource).

  Connector

• get_media

  Spytrend

  Fetch downloadable creative MEDIA (image/video URL + thumbnail) for 1-500 ad or creative UUIDs returned by search_ads / search_creatives. This is the paid delivery step. entity_type is 'ad' or 'creo'. Existing clients keep the {entity_type,items:[{id,media:[{media_type,url,thumbnail_url,fallback_urls}]}]} fields; additive counts, partial and failures explain malformed, quota-limited and unavailable items, plus interrupted items when at least one peer was delivered. Malformed/zero UUIDs never reach the API or consume quota; valid peers in a mixed batch are still processed. duplicate_count reports canonical duplicates, which are fetched and billed once. IMPORTANT: a blob coordinate can go stale after storage compaction, so if `url` returns an HTTP error (e.g. 416/404), retry fallback_urls in order before treating it as unavailable. Typical flow: search_ads (browse metadata, free) → pick ids → get_media. QUOTA: charges only for media actually delivered — 1 token per ad, 10 per creative (free starter: 500 tokens total; paid plans: 40,000/month). If your balance can't cover every id it delivers as many as fit. get_usage is free.

  Connector

• compare_evidence

  Healthy Aging Atlas

  Compare mapped human-evidence strength and limitations for two to five supplements for the same goal. This is an evidence comparison, not a product ranking or purchase recommendation, and contains no affiliate links. Use only for public, non-personal evidence questions. Do not call this tool for requests involving personal or sensitive health information, including medical records, medication lists, diagnoses, symptoms, laboratory results, or treatment planning. Tell the user not to submit that information and direct them to a qualified healthcare professional.

  Connector

• list_categories

  ContextOverflow

  The eight thinking-failure problems ContextOverflow covers, phrased the way a human experiences them. Start here to see what exists.

  Connector

• creative_get_authoring_contract

  Heista

  Read the canonical shelves, taxonomy, relationship Lego, safe content rules, and positional slots for every publishable Creative Library format. Call this before authoring.

  Connector

• get_embedder_network_manifest

  Storyflo

  Wrap the public ``/embed/network-manifest.json`` — the platform-level DSP/SSP onboarding bundle: supported creative formats, payout rails, attribution URLs, integration patterns. Use when an agent is evaluating whether to wire storyflo into its surface, or when a DSP partner needs the canonical integration shape. Public — no auth required.

  Connector

• get_critical_path

  Ganty MCP

  Calculate the critical path of a project on the Ganty side and return it as data (don't ask the model to reason over raw task lists). Uses forward/backward CPM with progress-aware remaining duration. Returns critical_path tasks in order, per-task earliest/latest start/finish + slack, project_end_date, and total_duration_days. v1 limitations: Finish-to-Start dependencies only (Ganty has no other types), calendar days by default (business_days=true skips Sat/Sun but no holiday table), ignores multi-period segments, no resource calendars. Returns { error: 'cyclic_dependency', cycle } if a cycle is detected.

  Connector