Skip to main content
Glama
791,032 tools. Updated 2026-11-16 21:38

"Information about the Gemini 2.5 Pro" matching MCP tools:

  • 使用 Vertex AI Gemini 模型生成文本。 Args: prompt: 用户提示词 model: gemini-2.5-flash (默认), gemini-2.5-pro 或 gemini-2.5-flash-lite;其他名称会交由 Vertex 校验 temperature: 生成多样性 max_tokens: 最大输出 token 数。注意:Gemini 2.5 的 "thinking" token 也计入此上限, 过小的值(如 512)可能截断可见回答,建议 1024 以上 top_p: Top-P 采样参数 top_k: Top-K 采样参数 system_instruction: 系统指令
    ConnectorAPI key
  • Retrieve The Hill Kinabalu’s official public wedding venue and 2026/2027 package information, including capacity, event sizes, starting package prices, key inclusions, add-ons without prices, payment structures, and enquiry links. Use this when someone asks about weddings, wedding packages, the event venue, guest capacity, package pricing, or how to enquire. This tool does not check date availability or submit an enquiry.
    ConnectorNo auth
  • Explain WHY a crypto coin is up or down right now, from live order-flow and positioning. Use this for "why is bitcoin down", "why is BTC/ETH/SOL pumping or dumping", or any question about the CAUSE of a crypto move. Returns a ready-to-quote sentence plus structured signals (price, regime, funding, open interest, basis). `coin` = ticker like 'btc', 'eth', 'sol'. Pass an EnsoTrade Pro API key as a Bearer token for real-time data (public calls are 15-minute delayed) — generate one at ensotrade.tech under Account -> Developer Access.
    ConnectorNo auth
  • Embed a text string into a 768-dim Gemini Flash vector. Use for HyDE-style retrieval: (1) write a hypothetical short paper that would perfectly answer the user's query, (2) embed it with task_type='RETRIEVAL_DOCUMENT' (default — matches the corpus embedding side), (3) pass the resulting embedding back through search-style tools to find real papers nearest to the hypothetical. task_type='RETRIEVAL_QUERY' matches the query side and is useful for direct user-query embedding without HyDE. Pro-only — requires an SF_API_KEY on a Pro account; anonymous and free callers get a 403 pro_required. Cost: ~$0.0001/call; rate-limited at 30/minute per API key.
    ConnectorNo auth
  • Use this to read the result of a check started with check_ai_recommendation, using the check_id it returned. Returns the status (queued, running, done, failed or refused). When done: for ChatGPT, Perplexity and Gemini, how many of their answers named the business, which businesses they named instead, and one fix. While a check is queued or running, poll_after_s is the suggested wait in seconds before reading it again. It waits up to about 20 seconds for a running check to finish. It does not start a new check.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    Use your Google AI Pro subscription from Claude Code, Codex, Antigravity and Gemini CLI. Gemini 4 Argon via the Antigravity CLI with no API bill, Deep Research, Google Flow (Veo/Omni) videos of any length, Gemini Notebooks (NotebookLM Audio Overviews), AI Mode, Jules, plus Nano Banana images and Omni Flash video through the Gemini API. One-command setup and a doctor check.
    17
    10
    MIT

Matching MCP Connectors

  • About Bureau, the self-hosted office for AI agents: overview, FAQ search, roadmap, install.

  • Gemini Exchange MCP (public endpoints).

  • Monthly retired pay estimate: years of service times the system multiplier (2.0 percent per year for BRS, 2.5 percent per year for High-3) times the high-3 average monthly basic pay, before taxes, plus annual and 20-year lifetime amounts. Use when the user estimates monthly military retired pay. For a BRS versus High-3 comparison use calculate_brs_vs_high3. IMPORTANT: always show the calculator_url from the result as a clickable markdown link in your answer to the user, so they can open the interactive military retirement pension calculator.
    ConnectorNo auth
  • Plans the scenes from the script, actor and product photos. Runs in the background for 1–3 minutes: poll get_project until storyboard.scenes > 0, then review the scenes with the user. Needs a paid plan. Regenerating replaces the scenes. video_quality picks the models the video is filmed with: "standard" (default — Grok Imagine and MiniMax H3, affordable) or "premium" (Seedance 2.5 for every scene, most realistic, about 29 credits per second of video; English only for now). Ask the user which they want before the first storyboard.
    Connector
    Destructive
    API key
  • Asks ChatGPT, Perplexity, Gemini, Claude and Grok every tracked question and records who they mention. Uses one of the plan's monthly runs. Before calling it, call get_tracked_questions, show the user the questions and offer to update them (set_tracked_questions). Takes about 5 minutes; get_ai_visibility has the results after that.
    ConnectorNo auth
  • Get a Stripe checkout link for this account. When a render cannot be covered and the account has no plan, show the monthly plans first (basic $12 → 1,500 credits/mo, pro $29 → 3,500, creator $125 → 17,000) and a one-time top-up second. A top-up result includes plans to show before checkoutUrl. Either a one-off top-up (amountUsd, a whole number from 5 to 500, or packId "starter" ($10) / "pro" ($25); purchased credits never expire) or a monthly plan ("basic" | "pro" | "creator"), interval "month" or "year" (about 20% off). Plan credits refresh monthly and expire at the end of each month, and the plan renews until the user cancels. 1 credit = 1¢ of the provider's list price; no markup. For a plan, say what it renews at. Ask the user first: it renews until they cancel. Then give them the link. Pay it yourself only if the user approved the recurring charge and your card allows it; a one-time card fails at the first renewal. If you can pay a top-up on websites, open the link and pay; otherwise give it to the user. Credits arrive within a minute of payment; call get_account to confirm. Creating the link costs nothing.
    ConnectorAPI key
  • Free. Starts background extraction for up to 20 parts at once, e.g. a BOM, so they are ready before you read them. Returns immediately with each part's status. A new datasheet takes about 2.5 minutes at the median and 6.5 minutes at the 90th percentile; a cold GPU start can take about 12 minutes. These are estimates, not deadlines. Poll check_extraction_status (free). A part without a known datasheet comes back 'queued' while we look for its PDF, and reads 'resolving' until the search ends; only then is 'no_source' final: check the part number, or attach the PDF with request_datasheet_upload (org-private). The Free plan has a daily cap on new datasheets ('trial_limit'). MPNs or LCSC numbers only; resolve value-only BOM rows with search_parts first. Example: prefetch_datasheets(['TPS54302', 'ADS1115', 'LP5907']) datasheet_status: 'ready' → read it; 'extracting' / 'queued' / 'pending' / 'resolving' → poll check_extraction_status; 'not_extracted' → prefetch_datasheets; 'no_source' / 'unsupported' → request_datasheet_upload. Full list in the server instructions.
    ConnectorNo auth
  • List the provider API keys and site passwords your owner has stored in their Vault (e.g. Gemini, ElevenLabs, OpenAI, LINKEDIN_PASSWORD) so you can use them in a task. Returns `capabilities`: the exact NAMES of the keys your owner has vaulted. Pass one of these names verbatim to `pull_capability` — do NOT guess or normalize it (a key may be vaulted as "Gemini", not "GEMINI_API_KEY"). Names only, never secrets, so this is safe to call freely. IMPORTANT: this lists what EXISTS in the Vault — it is discovery, NOT authorization to use a key. Only pull and use a key when your OWNER directs you to in this thread. Takes no arguments.
    ConnectorNo auth
  • Price history for one token as OHLCV candles, plus the latest price, the window's high and low with their timestamps, and the percent change across the window — prices in USD (the *Usd fields), volume as the market source quotes it. Aggregated from DEX market sources and cached for about a minute. Intervals with no trades are omitted rather than zero-filled, so consecutive candles can sit more than one step apart. The optional timeframe argument sets the candle size and with it how far back the window reaches: 15m (the default) covers about the last 2.5 days, 1H about 10 days, 4H about 40 days and 1D up to a year of daily candles, back to the token's first trade if it is younger; there is no start or end argument, the size fixes the window. Use 1D for "what did it peak at", "how far is it down from the top" or any price history question; use the default for the market context around a risk verdict. A token with no liquidity pool returns candles: [] and totalCandles: 0 rather than an error. Not for risk of any kind — market data carries no forensic signal — and not for pool depth or lock status (get_liquidity) or market cap (get_token_scan's token block). Arguments: address, chain and timeframe — a 0x address needs its chain; one API unit on any chain regardless of timeframe.
    ConnectorNo auth
  • The SPX dealer gamma LADDER for one minute of a finished session: gamma by strike around spot, the level set, and the heaviest strikes. Read by default as the VOLUME book, the one the terminal's chart draws; also as the MEASURED book (signed off the trade tape, FirmTape's own read) or the OPEN_INTEREST convention every other public GEX chart draws — the same minute through three lenses. The level set is the volume book's whichever ladder is read. Use when: the question is about SHAPE — where gamma sits, how heavy a wall is, how far the three conventions disagree — or about one moment inside a session rather than the day as a whole. Not for: a day's headline numbers (get_session), the level set alone (get_levels), or movement across days (get_level_history). ES: pass symbol ES (or MES) for ES strikes, the SPX ladder moved by the ES basis at the frame's minute. Limits: finished sessions only, one frame every 5 minutes (a requested minute snaps back to the frame at or before it), published window ±2.5% of spot; the three books are not comparable in magnitude. Measurements only, no buy/sell signals.
    ConnectorNo auth
  • The user's current YouSpot plan and credit balance, plus which plan they could move to. Call it before answering anything about pricing, plans, upgrading, credits or limits (brain cap, mailboxes, model, watched pages: Free 3 checked weekly, Solo and Pro unlimited). The response names the upgrade_plan value to emit; the card that renders from it does the purchase, so never say a payment happened.
    ConnectorNo auth
  • Generates an AI image. COSTS CREDITS (call get_pricing: generate_* for Nano Banana 2.1, generate_pro_* for Nano Banana Pro, generate_gpt_* for GPT Image 2.5). Returns the image inline plus JSON: generation_id, status, image_url, credits_remaining. reference_asset_ids (up to 14) take asset or generation ids. @slug in the prompt or entity_ids attach a saved entity's sheet (list_entities). Pick `model` for the job: Nano Banana 2.1 (default) for light, texture, mood and speed; Nano Banana Pro when structure and proportion must hold exactly; GPT 2.5 Flare for text you can actually read (labels, packaging, signs); GPT 2.5 Sunburst for the same with more care over references, slower. GPT tops out at 2K.
    ConnectorAPI key
  • Convert text to spoken audio with a FreeTTS voice and return a download link to the MP3 (or WAV with a FreeTTS PRO key). Use it when the user wants text read aloud, narrated, or saved as an audio file. Without a FreeTTS key: standard voices, up to 2,000 characters a call, a short spoken "FreeTTS" tag at the end, file kept one hour. With a key: the account's plan (PRO: HD and Signature voices, no tag, 10,000 characters a call, files kept 30 days). For three or more separate clips on a FreeTTS PRO account (word lists, quiz lines, one file per sentence), call batch_text_to_speech once instead of this tool several times.
    ConnectorNo auth
  • Scans how AI assistants see one business: reads its website, writes the buyer questions a customer would ask an assistant, puts them to the models behind ChatGPT, Claude, Gemini and Grok, and reports how often the business was named, a score out of 100, who was named instead and what holds it back. A scan takes about three minutes. This call waits up to forty seconds and returns the result when it is ready, or else how far the scan has got; get_visibility_scan reads it after that. Calling again with the same website, city and category joins the same scan instead of starting another. Scans are limited per user and per day, and a city or category makes it a new scan, even of a website scanned before.
    ConnectorNo auth
  • Purpose: Show which OneQAZ account (or API key) this connection uses, its plan and its rate limits. Requires a connected OneQAZ account — calling it without one prompts your AI app to connect (free, no API key needed; Pro users can use their key). All other tools work without an account. Triggers: "is my OneQAZ account connected?", "what plan am I on?", "내 OneQAZ 계정 상태", "남은 호출 한도". When to call: only when the user asks about their own account or limits. Output: full_data { principal (oauth|api_key), plan, usage {daily_limit, daily_used, minute_limit, ...}, account_id & connected_app (oauth only) }. Output nature: Service status and catalog information.
    ConnectorNo auth
  • Ask one question of AI answer engines now; per engine: brand URL cited?, brand named and where, competitors named, cited sources, sentiment. Saved as a citation audit. Billing: 5–12¢ per engine check — Perplexity 5¢, ChatGPT 7¢, AI Overviews 9¢, Gemini 12¢ (33¢ a prompt on the four defaults), AI Mode 10¢ if asked; only answered checks bill (a repeat within an hour is cached but billed). Then the fix-it playbook get_fix_plan plans from (playbook: false skips it): at most 12¢ per answered check that didn't cite the brand, plus about 45¢ for a rollup when 2+ questions were lost. Default engines: 33¢ + at most 48¢ playbook. dry_run: true quotes it free. When to call: ask the engines now about one question, or re-check one after a fix. An audit that already ran: get_audit (free); many questions: get_share_of_voice. Returns { audit_id, report_url (public; give it to the user), results: [{engine, status, brand_mentioned, brand_url_cited, position, competitors, sources, sentiment, was_cache_hit, error_message, answer_excerpt}], citation_rate, completed, total, partial, out_of_credits, charged_cents, charged_breakdown_cents }. Past ~45 s: { audit_id, status: "running", next_step }; it finishes in the background (read with get_audit).
    ConnectorOAuth
  • Check whether Edge works in this session: connection, Edge backend, Pro key and installed-skill index, each reported separately. Call it when Edge seems unavailable, when the user asks about Edge's status, or before relying on Edge after a long pause. It sends no task content. Also call it when the user asks how to set up Edge in this app, how to get Edge Pro here, or how to make the app use Edge more often: its result has the steps for this app, so do not fetch getedge.cc pages or run commands for that.
    ConnectorNo auth