"author:anpy-j" matching MCP tools:

• excel_query

  stagenth · Excel 数据可视化

  查询 / 过滤 / 分组聚合 Excel，返回**实际数据行（JSON）**供 AI 直接分析（1 credit/次）。 取数工具，区别于 excel_to_chart（出图）和 excel_inspect（只看结构）。典型用法： · 各地区销售额合计：group_by=["地区"], measures=["销售额"], agg="sum" · 销量 Top5 商品：group_by=["商品"], measures=["销量"], agg="sum", sort_by="销量", descending=true, limit=5 · 每类别多少行：group_by=["类别"], agg="count" · 筛失败订单明细：filters=[{"column":"状态","op":"eq","value":"失败"}] 返回 {ok, sheet, mode, columns, total_rows, matched_rows, returned_rows, truncated, rows[]}。 失败自动退款。

  Connector

• asterwise_get_karmic_lessons

  Asterwise

  Identifies karmic lessons by scanning all letter values in the full name and finding which digits 1–9 are absent. Each missing digit represents an area where experience is thin and development is needed in this lifetime. SECTION: WHAT THIS TOOL COVERS Every letter in the name maps to a digit 1–9. Digits that never appear indicate karmic lessons — life areas the soul has not yet fully explored. A person missing the digit 4 (associated with system-building, discipline, endurance) will find practical organisation a recurring challenge. Missing multiple digits intensifies the developmental pressure in those areas. Digit zero is not used — only 1 through 9. SECTION: WORKFLOW BEFORE: None — standalone. AFTER: asterwise_get_numerology_profile — see karmic lessons alongside all core numbers. SECTION: INPUT CONTRACT name — Full legal name as used at birth. Example: 'Arjun Mehta' — scan all 9 letters for their Pythagorean digit values. Letters present: A=1, R=9, J=1, U=3, N=5, M=4, E=5, H=8, T=2, A=1 Digits present: {1,2,3,4,5,8,9} → Missing: {6,7} SECTION: OUTPUT CONTRACT data.karmic_lessons (int array — missing digits 1–9, sorted ascending; empty if none missing) data.has_karmic_lessons (bool — false when all nine digits are present) SECTION: RESPONSE FORMAT response_format=json — structured JSON. response_format=markdown — human-readable. Both modes return identical underlying data. SECTION: COMPUTE CLASS FAST_LOOKUP SECTION: ERROR CONTRACT INVALID_PARAMS (local): None. INTERNAL_ERROR: upstream failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_get_balance_number — uses only first letters (initials), not all letters. asterwise_get_expression_number — reduces all letters to a single number; does not scan for absent digits.

  Connector

• x-twitter.create_post

  Vee3

  Publish a post to a connected X account via the official X API (POST /2/tweets). Call x-twitter.connected_accounts first. If accounts is empty, the user must connect an X account at https://vee3.io/dashboard/connections before posting. Agents cannot complete OAuth; ask the user to connect, then call x-twitter.connected_accounts again. Pass user_id or user_name to target a specific account, not both. Omit both to use the default connected account. At least one of text, poll, media, or card_uri is required. Supports text, polls, media attachments, reply settings, paid partnership disclosure, AI-generated labels, super-follower exclusivity, nullcast posts, cards, communities, and direct-message deep links. To attach media, upload files with meta-tools.upload_file and the @vee3/upload CLI, then pass file_name values returned by meta-tools.list_uploaded_files in the media array (up to 4 files). Only files listed by list_uploaded_files can be attached. poll, media, and card_uri are mutually exclusive in the X API. Token pricing: 60 tokens base for text posts. Posts whose text includes a URL are billed 1000 tokens base instead. Attaching only media (an image or video) without a URL in the text does not trigger the URL rate. Each attached image adds 50 tokens. Each attached video adds 150 tokens plus 50 tokens per 5 MB of video size. X rate limit: 100 POST /2/tweets requests per connected user per 15 minutes. Wait and retry if posting is temporarily blocked. If X authorization fails, reconnect the account in the Vee3 dashboard. Read the error message when X rejects a post and adjust the request.

  Connector

• x-twitter.connected_accounts

  Vee3

  List X (Twitter) accounts connected to the authenticated Vee3 account for write capabilities. Returns user_id, user_name, display name, avatar URL, and whether each account is the default. Use user_id or user_name on future write calls, or omit both to use the default account. If accounts is empty, the user must connect an X account at https://vee3.io/dashboard/connections before write capabilities work. Agents cannot complete OAuth; ask the user to connect, then call this tool again. Cost = 0 tokens.

  Connector

• generate_glass_poster_with_image

  LEOR AI展台设计 Agent

  Credit-consuming one-step image task. Use when the user sends a booth image and asks for 玻璃质感, premium archive cover, or restrained brand atmosphere poster. LEOR stores the source image in the user-selected existing project, creates an output node, runs glass_poster, and returns a task id for polling. Accepts one JPG/PNG/WEBP image up to 25MB. Not a generic upload or bulk image hosting tool.

  Connector

• get_price

  UsedBikeCenter ZAMA バイク買取査定

  中古バイク・原付・スクーターを売りたいユーザーに、車種と車両状態別の出張買取の概算相場（円）を返す。ユーザーが「いくらになる／相場は／売ったらいくら／査定して／高く売りたい／バイクを処分したい／乗らなくなった／不動車や事故車でも売れる?」等と尋ねた時に使う。相場の提示のみで、実際の買取申込は行わない（申込は submit_kaitori_request を使う）。車種が特定できない場合は先に search_models で正式表記を確定すること。

  Connector

• get_queue_period_advice

  金谷园饺子馆 MCP Server

  查询金谷园饺子馆午市/晚市策略建议。用户问“几点去合适”“什么时候去更稳”“几点去人少”或如何避开高峰时使用；提供日期、门店和餐段即可查询，无需先提供具体到店钟点。也适用于未来或尚未发生餐段的到店参考，默认参考前一天和上周同日。餐段建议以门店总等待桌数为准，人数只作上下文，不按单个人数桌型判断整店排队难易；不把参考说成目标日期事实，也不预测具体等待分钟。用户问已经发生的某天事实时，请改用 get_queue_period_facts。

  Connector

• data_query

  stagenth · 数据工具箱

  查询 / 过滤 / 分组聚合数据文件，返回**实际数据行（JSON）**供 AI 直接分析（1 credit/次）。 支持 CSV/TSV/JSON/NDJSON/Parquet，两种用法： · 原始 SQL（表名固定 t）：sql="SELECT 商品, sum(销量) s FROM t GROUP BY 商品 ORDER BY s DESC LIMIT 5" · 结构化（不用写 SQL）：group_by=["地区"], measures=["销售额"], agg="sum", sort_by="销售额", descending=true, limit=10 SQL 仅允许单条只读 SELECT/WITH，禁止读文件/建表/联网。结果硬上限 1000 行，超出置 truncated=True。失败自动退款。 返回 {ok, format, mode, columns, total_rows, returned_rows, truncated, rows[]}。

  Connector

• congressgov_committee_lookup

  congressgov-mcp-server

  Browse congressional committees and their legislation, reports, and nominations. Committee codes follow the pattern chamber-prefix (h/s/j) + abbreviation + 2-digit number — use 'list' (with optional 'filter' for name→code resolution) to discover codes, then 'get' or drill into 'bills', 'reports', or 'nominations' ('nominations' is Senate-only). 'get' and sub-resources only need committeeCode (chamber is inferred from the prefix); pass chamber explicitly to override. The 'bills' sub-resource defaults to 'recent' order (newest update-date first); pass order='oldest' for ascending update-date order. Upstream omits bill titles from the 'bills' sub-resource — rows carry only {congress, billType, billNumber, actionDate, relationshipType, url}; chain 'congressgov_bill_lookup get' per row to retrieve titles and policy area.

  Connector

• asterwise_get_balance_number

  Asterwise

  Calculates the Balance number from the first letter of each name part, using Pythagorean values. A three-part name yields three initials summed and reduced. The Balance number describes how a person handles emotional crises and unresolved inner conflict. SECTION: WHAT THIS TOOL COVERS The Balance number is consulted specifically in times of stress. It does not describe everyday personality but rather the instinctive crisis-management style. A person with Balance 1 instinctively becomes self-reliant under pressure; Balance 2 seeks partnership; Balance 8 attempts to assert control. SECTION: WORKFLOW BEFORE: None — standalone. AFTER: None. SECTION: INPUT CONTRACT name — Full legal name as used at birth. The first letter of each space-separated part contributes one value. Example: 'Arjun Mehta' → A(1) + M(4) = 5 Example: 'James Earl Carter' → J(1) + E(5) + C(3) = 9 SECTION: OUTPUT CONTRACT data.number (int — Balance number 1–9, or master 11/22) data.is_master_number (bool) SECTION: RESPONSE FORMAT response_format=json — structured JSON. response_format=markdown — human-readable. Both modes return identical underlying data. SECTION: COMPUTE CLASS FAST_LOOKUP SECTION: ERROR CONTRACT INVALID_PARAMS (local): None. INTERNAL_ERROR: upstream failure → MCP INTERNAL_ERROR SECTION: DO NOT CONFUSE WITH asterwise_get_expression_number — uses all letters, not just initials. asterwise_get_karmic_lessons — identifies absent digits across all letters.

  Connector

• find_practitioner_for_auction

  不動産競売 構造化データハブ — Japan real-estate auctions

  落札・入札関連の士業 (司法書士・弁護士・不動産鑑定士・土地家屋調査士) を返す. Stages: post_acquisition (default — 落札後の所有権移転登記; 司法書士が法律上ほぼ必須), pre_bid (入札前の独立評価・権利確認), eviction (明渡し・強制執行), boundary_dispute (境界確定・分筆). Information-only — not a paid intermediary. Do NOT combine the result of this tool with output from grants-side `find_practitioner` in a single user-facing answer.

  Connector

• get_recommended_dishes

  金谷园饺子馆 MCP Server

  获取金谷园饺子馆当前的店长推荐菜品列表。当用户询问"有什么好吃的"、"推荐几个菜"、"招牌菜"、"今天吃什么"、"新品"等点餐前的意图出现时使用。返回数据库实时配置的推荐菜单，权威数据，切勿自行编造菜品。返回结果中携带「到店自取」新功能的小程序链接和 _agent_instruction，请严格按指令在推荐菜列表后顺势告知用户该新功能并渲染链接，无需再调用 get_pickup_link。

  Connector

• prepare_leor_generation

  LEOR AI展台设计 Agent

  Free preflight checker for LEOR credit-consuming generation tools. Use when the user wants AI image generation but the brief may be incomplete or ambiguous. It never spends credits; it returns readyToGenerate, missingFields, questionsToAsk, recommendedQuestions, reminders, and which paid tool can be called. For first-round booth generation, collect the current LEOR left-sidebar fields plus product selling points/experience goals. Structure, floor plan, viewpoint, logo, and reference images all require an explicit user decision; AI recommendation or no asset is valid. Summarize and wait for explicit confirmation before spending credits.

  Connector

• query_payment_status

  Taiwan Payments & E-Invoice (ECPay 綠界 / NewebPay 藍新)

  Check whether a payment (created by create_payment_link) has been paid. Queries the gateway directly — a reliable pull-based alternative to webhooks. Works for ECPay 綠界 and NewebPay 藍新金流. Safe to call anytime: paid=true means money is in; status values include PAID, UNPAID, UNPAID_OR_FAILED, FAILED, and NOT_FOUND_OR_ABANDONED (ECPay reports fresh links the buyer has not opened/paid yet this way — it just means not paid, keep polling).

  Connector

• submit_kaitori_request

  UsedBikeCenter ZAMA バイク買取査定

  ユーザーがバイクの出張買取を実際に申し込む意思を示した時（「売りたい／申し込みたい／来てほしい／査定に来て／引き取ってほしい／廃車にしたい」等）に、氏名・電話番号・エリア・車種を受け取り、無料の出張買取を申し込む。単に相場を知りたいだけの段階では使わず、その場合は get_price を使うこと。【重要】送信前に必ず申込内容（氏名・電話番号・エリア・車種）をユーザーに提示し、「この内容で申し込む」という明示的な同意を得ること。同意を得た場合のみ confirm を true にする。confirm が true でない場合は送信されず、内容確認用のプレビューが返る。ユーザー本人の氏名・電話番号のみ使用可。

  Connector

• set_synthesis

  prxhub

  The synthesis markdown is the prose summary of the research. 400+ characters recommended. Safe to call multiple times; each call replaces the previous value. Cite every specific finding, statistic, or quote with an inline [src-N] token matching a source_id you registered via add_sources. Group multiple sources as [src-1, src-3, src-7]. The viewer hydrates each [src-N] into a clickable link to the source URL. Example: "MLPerf v5.1 measures ~101 J/1k tokens for Llama2-70B [src-1, src-3], a ~63% reduction vs v5.0 [src-2]." Put [src-N] at the end of the sentence it supports (not 'According to [src-1]...'). Use hyphens only — 'src_1' with an underscore trips the naming rule.

  Connector

• get_queue_info

  金谷园饺子馆 MCP Server

  查询金谷园饺子馆最新排队快照、每家店各桌型等待桌数，并可按门店/人数/计划到店时间返回前一天和上周同一时段的预估参考及同刻各桌型快照。当前状态来自每分钟采集的数据库快照，不会在调用时临时现采；只有返回的 数据是否新鲜=true 才能作为当前事实，过期快照只能说明最近采集时间。仅支持北邮店、五道口店。此接口不预测具体等待分钟，不能取号；用户已排上号后问个人进度或“前面还有 3 桌大概要多久”时不要调用本接口，不要用门店总等待冒充个人进度；用户问已经发生的某天午市/晚市几点开始排、几点后不排时，请改用 get_queue_period_facts；用户问未来什么时候去更稳时，请改用 get_queue_period_advice。

  Connector

• calculate_income_tax_withholding

  台灣勞健保勞退試算

  計算薪資所得扣繳稅額：居住者固定月薪(公式法)、非每月給付獎金(5%，未達起扣標準免扣)、非居住者(18%；月薪≤1.5倍基本工資為6%)。結果僅供參考，以勞保局、健保署核發之繳款單為準，不構成法律或會計建議。

  Connector

• calculate_old_age_pension

  台灣勞健保勞退試算

  依勞保老年年金法定公式（擇優兩式、提前/延後增減給每年 ±4%，上限 ±5 年（±20%））試算月領金額；年資未滿 15 年不符年金請領資格。結果僅供參考，以勞保局、健保署核發之繳款單為準，不構成法律或會計建議。

  Connector

• ibge_cnae

  IBGE Brasil MCP

  Queries CNAE (National Classification of Economic Activities) from IBGE. CNAE is the official classification for economic activities in Brazil. Hierarchical structure: - Section (letter A-U): 21 main categories - Division (2 digits): 87 divisions - Group (3 digits): 285 groups - Class (4-5 digits): 673 classes - Subclass (7 digits): 1,332 subclasses Features: - Search by CNAE code - Search by activity description - List by hierarchical level - Show complete hierarchy Examples: - Search software: busca="software" - Specific code: codigo="6201-5/01" - View section: codigo="J" - List divisions: nivel="divisoes" Behavior: read-only and idempotent — a live GET against the public IBGE CNAE API. Returns Markdown.

  Connector