"How to create a WeChat Mini Program" matching MCP tools:

• get_project_info

  Fractera

  Project reference / help desk about Fractera. Use this to answer ANY user question about what Fractera is, how it works, its architecture, components, modes, data ownership, pricing, use cases, partner program, etc. — especially while a deploy is running and the user wants to learn more. TOKEN-ECONOMY: call with NO arguments first to get the lightweight list of section ids+titles, then call again with a single `section` id to fetch just that section. NEVER try to fetch everything at once; pull only the section(s) relevant to the user question. Set `lang:"ru"` for Russian-speaking users.

  Connector

• get_project_info

  Fractera

  Project reference / help desk about Fractera. Use this to answer ANY user question about what Fractera is, how it works, its architecture, components, modes, data ownership, pricing, use cases, partner program, etc. — especially while a deploy is running and the user wants to learn more. TOKEN-ECONOMY: call with NO arguments first to get the lightweight list of section ids+titles, then call again with a single `section` id to fetch just that section. NEVER try to fetch everything at once; pull only the section(s) relevant to the user question. Set `lang:"ru"` for Russian-speaking users.

  Connector

• partner_program_info

  HelloBooks AI Agents MCP Server

  Return the HelloBooks Partner Program structure — free reseller channel for accountants/CPAs/bookkeepers who put their clients on Pro/Business plans. Earned wholesale discount model (no commission): Bronze 5% at 25 pts / Silver 10% at 75 / Gold 15% at 300 / Platinum 20% at 1,000+. Pro client = 1 pt/mo, Business client = 4 pts/mo. Call with no args for the full ladder + meta; with `points` for current status + how many points to next tier; with `proClients` and/or `businessClients` to derive points from the client book and then return the same status verdict. The Partner Program is the `cpa` plan id in list_plans (the retired $59.99 SKU is gone). HelloCPA Practice Management at practice.hellobooks.ai is a different product and NOT the Partner Program.

  Connector

• pricetik_hotel_get_booking_url

  mcp-server

  Generate a one-click signed PriceTik checkout URL for a hotel stay. Stay-based form (preferred for agents): pass providerPropertyId + checkIn/checkOut + guests/rooms (+ optional roomCode) and the server resolves the best live rate itself. Or pass a rateKey from pricetik_hotel_price_check directly; it auto-refreshes near expiry or when rateType is "RECHECK". URLs are pricetik.com/go/ affiliate redirects — pass to the user's browser unchanged, never fetch server-side. On 410 RateKeyExpired, re-call pricetik_hotel_price_check for a fresh rateKey. On 422 PackagingDenied, the rate is package-only and can't be booked hotel-only. currentBest surfaces nightlyRate, totalStayCost, currency, paymentType, rateType, freeCancellation only — no margin fields. When a stored loyalty program matches the property's chain, the response carries loyaltyApplied ({ program, memberId }) and the URL is member-stamped — tell the user which program linked.

  Connector

• play_game

  Vocab Voyage

  Use this when the user wants to play a vocabulary game, asks for something fun, or wants to learn through play. Launches one of 11 mini-games inside the host chat. Renders the matching ui://vocab-voyage/game/{slug} widget on supporting hosts; falls back to a deep link elsewhere. Per-question answers persist via record_word_result; round completion fires record_session_complete + award_game_xp so MCP play counts toward streaks, XP, and mastery for signed-in users. Supported slugs: word_match, spelling_bee, speed_round, synonym_showdown, word_scramble, fill_in_blank, context_clues, word_guess, picture_match, crossword, word_search. Do not use for a serious test-prep quiz — call generate_quiz instead.

  Connector

• get_program

  Lodi Kids Activities

  Get full details for a single program by slug. Use this after `search_programs` returned a result and the user wants to know more — full description, schedule, registration timing, contact info.

  Connector

• create_channel_from_template

  PoolParty Main Stage Airtime

  Create a new PoolParty channel from an approved starter blueprint. Requires API key with create:channel scope. Creates channel + program + starter blocks in ACTIVE_UNLISTED state. Channel is not publicly discoverable until admin promotes it. Use list_channel_templates and preview_channel_template first to choose a template. Rate-limited: 3 per hour per key.

  Connector

• discovery_health

  aeX402 RPC (Solana + Robinhood Chain)

  Report the freshness and health of the cross-chain program/token discovery pipeline: when the hourly cron last ran, how many programs/tokens each chain scan produced, and which scans failed. Use this to check whether discover_programs / search_tokens data is current before relying on it.

  Connector

• create_funnel

  convalytics

  Create a new funnel on a project. Steps are 2–10 ordered events or pageview paths. conversionWindowMs caps how long a visitor has between consecutive steps (default 7 days); this is the step-to-step limit, without which a funnel is just event co-occurrence. Returns { id } on success.

  Connector

• aidefense_get_framework_alignment

  website-search

  Get AI Defense Matrix cross-mappings to nine external frameworks: NIST IR 8596, CSA AI Controls Matrix, ISO 42001, Google SAIF, SANS Critical AI Security Guidelines, MITRE ATLAS, OWASP AI Exchange, OWASP LLM Top 10, OWASP Agentic Security Top 10. Each row maps an AI asset class to how that framework applies. Each returned framework also carries a 'concepts' array of the structured IDs (MITRE ATLAS techniques, OWASP risks, ISO clauses) the matrix references for it. Supports a 'buyer' archetype shortcut to scope to the frameworks a particular buyer will care about. Use to translate between framework vocabularies. This server never requests your program docs or product roadmap and instructs your AI to keep them local—the matrix, framework alignments, and playbooks flow to your AI for local analysis.

  Connector

• aidefense_evaluate_program

  website-search

  Get the AI Defense Matrix evaluation playbook for assessing an AI security program: per-cell prompts, gap-inventory template, and a workflow that walks each asset class first and rolls findings up to the Govern column. Supports mode='gate' for binary deployment-gate decisions (returns the deployment-gate workflow plus gate-tier prompts only) and consumerPattern for scoping to consumed-vs-built AI deployments. The AI applies these prompts against your program documentation locally, and no program details leave your client. This server never requests your program docs or product roadmap and instructs your AI to keep them local—the matrix, framework alignments, and playbooks flow to your AI for local analysis.

  Connector

• draft_program_queue

  PoolParty Main Stage Airtime

  Save an ordered PP2 Program Queue draft from source candidate ids. Creates or reuses candidate-backed Program Queue items, applies the requested order, and optionally replaces/prunes stale draft items when replaceDraft=true. Requires write:program_queue scope. Does not publish or mutate the live queue.

  Connector

• apiosk_payment_guide

  Apiosk MCP

  Explain how to pay through the Apiosk gateway. Returns a buyer guide (how an agent settles a paid API call over USDC/x402, tailored to the current auth) and a provider guide (how to publish an API and get paid). Pass slug to scope buyer guidance to one listing, or role to pick a side.

  Connector

• tv_recommend_today

  rotv-mcp

  Returns up to N ranked program recommendations for a given timeframe. Uses a deterministic scorer that rewards films / documentaries / generalist channels, penalises news, and boosts programs starting within the next hour. Use for queries like "recommend me something for tonight", "ce e bun la TV diseară".

  Connector

• GetAtmPrograms

  equibles

  Get a company's at-the-market (ATM) equity offering programs — the dilution mirror-image of the buyback picture GetBuybackPrograms returns: establishment date, total capacity the company may sell "up to", cumulative amount sold, remaining availability with per-figure as-of dates, expiry, a derived exhausted/expired status, and source filings. ATM programs have no tagged XBRL equivalent, so figures come from verified extractions of the company's own 10-K, 10-Q and 8-K filings (offering-note prose and disclosure tables); only filings from roughly the last 13 months are scanned, so an empty result means no program was captured there — not proof the company runs no ATM program. Nothing is estimated.

  Connector

• college_value_score

  livedatalink

  One-call 'is this degree worth the cost' read for a US college (and optionally a named program). Joins the College Scorecard / IPEDS education domain (average net price, six-year completion rate, median earnings ten years after entry, and - when a program is named - program-level median debt and 1-year earnings) with a keyless BLS wage context (CES average hourly earnings, annualized) to place those earnings against the broad US private-sector wage. Returns a plain read - STRONG VALUE / FAIR / WEAK VALUE / INSUFFICIENT DATA - with the cost-vs-earnings evidence itemized and each sub-signal scored. A source that fails is noted, not fatal. Premium cross-source synthesis; Scorecard earnings cover federally-aided students only and lag by years. Informational only, not admissions, financial, or career advice.

  Connector

• get_treatment_types

  GTH Intelligence - Substance Abuse Treatment Finder

  Get definitions of all treatment program types (Inpatient Rehab, Detox, PHP, IOP, Outpatient, MAT, Counseling, Sober Living) with duration, intensity, and typical fit. Returns markdown-formatted explanations. Use when the user is uncertain which treatment_type to pass to search_facilities, or asks 'what's the difference between X and Y'.

  Connector

• hive_earn_register

  Hive Zk Attestation

  Register an agent for the Hive Civilization attribution payout program. Settlement on real Base USDC. 5% kickback on attributed traffic, weekly payout. Calls POST https://hivemorph.onrender.com/v1/earn/register on behalf of the caller. Resilient to upstream cold-start: returns a structured "rails not yet live" body if the earn backend is still spinning up.

  Connector

• count_tokens_multi

  Toolora MCP Server

  Estimate token count + USD cost for a text across every major LLM (GPT-4o, GPT-4o-mini, o1, o1-mini, Claude 3.5 Sonnet/Haiku, Claude 3 Opus, Gemini 1.5 Pro/Flash, Llama 3 70B/8B) in one call. Returns per-model: estimated tokens, context-window fit %, input cost, and roundtrip cost (input+output). Also returns the cheapest and costliest model that fits. Use this before sending a long context to decide which model to route to. One call replaces 11 separate tokenizer lookups.

  Connector

• estimate_llm_cost

  IA-QA — 130+ QA & Dev Tools for AI Agents

  Estimate the API cost in USD for a given model and token counts. Supports all major 2024–2026 models: GPT-4o, GPT-4.1, o3, o4-mini, Claude Opus 4, Claude Sonnet 4/4.5, Gemini 2.5 Pro/Flash, DeepSeek V3/R1, Grok 3, and legacy models.

  Connector