"The most widely used models" matching MCP tools:

• portugal_ifici_nhr_checkerA

  Xearno ToolsA

  Whether you qualify for Portugal’s IFICI — the activity-gated successor to the NHR regime that closed in 2024. Checks your eligibility for Portugal’s IFICI (Incentivo Fiscal à Investigação Científica e Inovação, widely called "NHR 2.0"): 20% flat tax on eligible-activity Portuguese income for 10 years, with most foreign income exempt. The old NHR closed to new entrants on 1 Jan 2024, yet general AI still tells people to "apply for NHR" and quotes its 10% foreign-pension rate — gone: IFICI taxes foreign pensions at full progressive rates. The real gate is an activity test across six routes with route-specific certifying entities (FCT, AT, ANI, Startup Portugal, AICEP) — this tool walks the gates in order and names the route, the certifier, and the registration deadline.

  ConnectorNo auth

• generate_imageA

  Galatic.aiA

  Generate images from a prompt. model is required by the server (400 without it): a model id from list_models, such as "flux-pro"; video models are refused. count makes 1-4 images and is charged per image. imageUrls is used only by image-to-image models, which require it; text-to-image models ignore it. Most models run in the background and return the id as job_id; a few answer at once with { images } already saved to the library. With count above 1, the status poll reports complete after the first image; find the rest with list_gallery. Spends Galatic.AI credits. Returns a job id; poll get_job_status with kind "image".

  ConnectorOAuth

• compare-models-side-by-sideA

  OptimTokenA

  Compare 2-4 named LLM models against all 8 use-case profiles at a chosen monthly volume, showing list and optimized cost for each. Use when the user names specific models to weigh against each other, rather than filtering the whole catalogue. If they also supply their own token counts, or a volume outside 10k/100k/1m, use estimate-llm-cost instead. Every name is resolved against the catalogue and the outcome is reported in `resolution` and in the text: a name that matched nothing, matched several models, or duplicated an earlier pick is stated explicitly, and such a name gets no column rather than a zero cost. Prices and costs are final as returned: rounded server-side and dated by `provenance`.

  ConnectorNo auth

• wait_for_new_blockA

  Parallax ProtocolA

  Waits until the chain has a block above "after_block" (default: the current head) and returns it: number, hash, parent hash, timestamp, miner, difficulty, gas used, transaction count and subsidy, with a reorg marker if the tip was replaced instead. Blocks come every 10 minutes on average, but intervals vary widely, so a wait can time out: then it returns "new_block": false with the current head, and you can call it again. "timeout_seconds" defaults to 120, at most 600 (90 on servers running without HTTP sessions). For clients that support resource subscriptions, subscribing to parallax://chain/head is the better way to follow the chain. Use this to wait for a transaction's next confirmation, then check it with get_receipt.

  ConnectorNo auth

• image_generateA

  HubrisA

  Draw an image from a text description with an image model from the Hubris catalogue (FLUX, Recraft, Seedream, GPT Image and others) and get the picture back right away as image content. Same as POST /v1/images/generations. Only models whose `tool` is "image_generate" work here. Models that draw inside a chat answer and also write text (Gemini Image, GPT-5 Image) have tool "chat_complete" and run there. Sizes such as 4K can be heavier than your client accepts in one answer — ask for 2K or less here. Spends money from the account balance: most image models are billed per image, some per megapixel or per token — models_get_pricing shows the price before you call. The charge shows up in usage_get.

  ConnectorAPI key

• calculate_ev_to_ebitdaA

  valuation-apiA

  Calculate the EV/EBITDA multiple: enterprise value divided by EBITDA — the most widely used valuation multiple for comparing companies independent of capital structure, tax and depreciation policy. Formula: EV/EBITDA = Enterprise Value / EBITDA. WHEN TO USE: Use for relative valuation of cash-generative businesses against peer multiples or transaction comps; a lower multiple may indicate relative undervaluation (or justified risk). WHEN NOT TO USE: Do NOT use when EBITDA is negative or near zero, or for early-stage companies with no meaningful EBITDA — the multiple is meaningless there (use EV/Revenue). BEHAVIOUR: pure deterministic calculation — no side effects, no network or storage access; idempotent and non-destructive; identical inputs always produce identical outputs. Division by zero, non-finite inputs, or mathematically undefined combinations return an explicit error instead of a number. RETURNS: JSON object { ev_to_ebitda: number (e.g. 8.5 = 8.5x), inputs }. PARAMETERS: enterprise_value (required): Enterprise value in currency units, e.g. 10000000. Must be > 0. ebitda (required): Earnings before interest, tax, depreciation and amortisation, e.g. 1200000. Must be > 0 for a meaningful multiple.

  ConnectorNo auth

• calculate_ev_to_ebitdaA

  valuation-apiA

  Calculate the EV/EBITDA multiple: enterprise value divided by EBITDA — the most widely used valuation multiple for comparing companies independent of capital structure, tax and depreciation policy. Formula: EV/EBITDA = Enterprise Value / EBITDA. WHEN TO USE: Use for relative valuation of cash-generative businesses against peer multiples or transaction comps; a lower multiple may indicate relative undervaluation (or justified risk). WHEN NOT TO USE: Do NOT use when EBITDA is negative or near zero, or for early-stage companies with no meaningful EBITDA — the multiple is meaningless there (use EV/Revenue). BEHAVIOUR: pure deterministic calculation — no side effects, no network or storage access; idempotent and non-destructive; identical inputs always produce identical outputs. Division by zero, non-finite inputs, or mathematically undefined combinations return an explicit error instead of a number. RETURNS: JSON object { ev_to_ebitda: number (e.g. 8.5 = 8.5x), inputs }. PARAMETERS: enterprise_value (required): Enterprise value in currency units, e.g. 10000000. Must be > 0. ebitda (required): Earnings before interest, tax, depreciation and amortisation, e.g. 1200000. Must be > 0 for a meaningful multiple.

  ConnectorNo auth

• calculate_ev_to_ebitdaA

  Valuation APIA

  Calculate the EV/EBITDA multiple: enterprise value divided by EBITDA — the most widely used valuation multiple for comparing companies independent of capital structure, tax and depreciation policy. Formula: EV/EBITDA = Enterprise Value / EBITDA. WHEN TO USE: Use for relative valuation of cash-generative businesses against peer multiples or transaction comps; a lower multiple may indicate relative undervaluation (or justified risk). WHEN NOT TO USE: Do NOT use when EBITDA is negative or near zero, or for early-stage companies with no meaningful EBITDA — the multiple is meaningless there (use EV/Revenue). BEHAVIOUR: pure deterministic calculation — no side effects, no network or storage access; idempotent and non-destructive; identical inputs always produce identical outputs. Division by zero, non-finite inputs, or mathematically undefined combinations return an explicit error instead of a number. RETURNS: JSON object { ev_to_ebitda: number (e.g. 8.5 = 8.5x), inputs }. PARAMETERS: enterprise_value (required): Enterprise value in currency units, e.g. 10000000. Must be > 0. ebitda (required): Earnings before interest, tax, depreciation and amortisation, e.g. 1200000. Must be > 0 for a meaningful multiple.

  ConnectorNo auth

• list_tagsA

  Spark Apps CatalogueA

  List every tag used across the Spark catalogue with how many apps carry it, most used first. Read-only. Use this before search_apps to pick a tag that actually exists.

  ConnectorNo auth

• ask_supportA

  WidelyB

  Writes a message into this user's Widely Support chat and notifies the Support team. A person on the team replies in that chat (not instantly); call read_support to get the reply. Any connected account can send it. text is what is needed and what was already tried.

  ConnectorOAuth

• add_antigravity_startA

  openFlowA

  Begin connecting a Google ANTIGRAVITY account (used by the Claude/Gemini models via OmniRoute — not a Google Flow account). Returns `authorize_url` and `state`. The next step is on the USER's side: give them `next_step` wording and the URL, they sign in and press Accept in their browser and hand you the `code=...` value from the antigravity.google/oauth-callback page. Then call add_antigravity_submit(code, state) with the `state` returned here.

  ConnectorNo auth

• get_storage_usageA

  FramevineA

  Get how much of the user's Framevine storage is used and how much is left: their plan, used, total and available bytes, percent used, how many days files are kept, and a breakdown into uploads, generations and hidden files. Check this before uploading large images or generating video, which take the most space. Use estimate_cost to see whether one specific generation will fit.

  ConnectorOAuth

• search_wake_word_libraryA

  wake-word-trainingA

  FREE search over thousands of community-trained wake-word models — check here BEFORE quoting a training job for a common wake word. Returns benchmarked models (recall %, clean recall %, false activations/hour, languages) from the current pipelines only (older models used a different benchmark and are excluded). Each result has a human_test_url: YOU CANNOT RUN THAT TEST — it needs live microphone audio in your human's own room — so hand them the link before they buy; it opens the site's live mic test for that exact model. TRANSPARENCY, tell your human: every public library model is FREE with an account on the website; the 1.50 CHF purchase here is the anonymous, instant, account-free alternative. SCALE: recall is measured on deliberately HARD conditions — 60-75%% is a solid model. Weak numbers or no match? Train a custom model with create_training_job instead.

  ConnectorNo auth

• run_promptA

  ZeroRank - Track and improve your AI search visibilityA

  Queue an on-demand run of an ACTIVE prompt across the workspace's enabled AI models (or a subset via `models`). Consumes answer-run budget per model (premium models weigh up to 20x): the monthly budget first (it resets on the 1st), then extra answers, which an owner or admin can buy in Settings → Billing and which never expire. Fails with ANSWER_RUNS_TOTAL_LIMIT when what is left of both cannot cover even the cheapest model being run. The result's `answerRuns` is { used, limit, credits } (credits = extra answers left; omitted for a workspace-only client). Answers land asynchronously a few minutes later — check list_chats. Limited to 5 run calls per minute.

  ConnectorOAuth

• compare_modelsA

  ModelSpecA

  What facts do 2 to 4 named models have? Returns sourced snapshot facts, offerings and evidence in caller order; unknowns stay null. Needs an API key (Authorization: Bearer). Costs 2 credits a call; $0.0053–$0.02 per credit by plan or pack (https://modelspec.dev/pricing/). It doesn't choose a model and does not rank. Proxies POST https://api.modelspec.dev/v1/compare-models with {models: [...]} at most 16 KB.

  ConnectorNo auth

• recent_quakesA

  Geonet NzA

  Recent New Zealand earthquakes from GeoNet (official NZ monitoring, GNS Science), filtered by minimum Modified Mercalli Intensity. MMI 3 ≈ widely felt, 5 ≈ damaging; -1 returns all located quakes. Returns magnitude, depth, locality, felt intensity, and coordinates, newest first. Keyless.

  ConnectorNo auth

• accept_errands_termsA

  WidelyB

  One-time acceptance of the Widely Errands terms, needed before any AI call or errand can dial. Without confirm it returns a short terms summary, the link to the full terms, and whether this user already accepted. Show that to the user; only after the user clearly agrees, call again with confirm=true to record the acceptance. Safe to repeat.

  ConnectorOAuth

• upload_hosted_model_versionA

  Last PriceA

  Upload a model trained anywhere as a new version of a hosted model: the ONNX file as base64 (at most 4 MiB) and the spec that maps request fields to its inputs. It is checked before it is stored: it must parse, use only operators the hosted runtime runs (scikit-learn, XGBoost and LightGBM tree ensembles, linear models, small neural networks), take as many inputs as the spec lists, and give a finite answer of the right shape on a test row; otherwise it answers 422 naming the problem. Stored as a candidate unless promote is true. The hosted MCP endpoint (/api/mcp/rpc) takes requests of at most 64 KiB, so send a larger file with the stdio server, the tool packages or POST /api/hosted-models/{model_id}/versions. Answers 404 not_released while hosted models (the hosted-pricing-models release) are not switched on for your workspace. Needs a Last Price credential with function publish scope. Needs a claimed workspace: a sandbox key from self-registration is refused (403) until a person claims the workspace.

  ConnectorNo auth

• startA

  AI-first company: evidence on AI adoptionA

  Start here for any question about adopting AI in a company: the map of the ai-first.company evidence. Returns the company cases by the kind of work AI was used for (customer service, legal work, office assistant and others), the six themes (with counts of practices, cases and studies), the claim checks of widely repeated AI statistics, the groups of other figures, the company cases by outcome, the assessments by kind, and what each filter value and rating means. Then open the part that fits and fetch records with get_evidence.

  ConnectorNo auth

• herb_at_a_glanceA

  Nih SupplementsA

  A popular herb's science-and-safety summary from NIH's National Center for Complementary and Integrative Health (NCCIH) 'Herbs at a Glance' series — what the science says, side effects and cautions, and key references. Covers ~56 widely-used herbs (turmeric, ginkgo, echinacea, garlic, ginseng, milk thistle, St. John's Wort, and more) that NIH's Office of Dietary Supplements does NOT have its own fact sheet for. For a vitamin, mineral, or the handful of botanicals ODS does cover (ashwagandha, black cohosh, valerian), use supplement_factsheet instead.

  ConnectorNo auth

• verify_callback_channelA

  WidelyB

  Confirms a callback channel. Pass the code for email, SMS, or WhatsApp. A webhook or Widely chat is checked again with a test message. If the code has expired or is locked, call resend_callback_channel_code.

  ConnectorOAuth