原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

Namaste America

✓ 服务方 · namasteamerica.us

作者:manvigallc007-spec版本 0.1.0i★ 0i在云端运行官方网站 ↗
注册名称us.namasteamerica/namaste-america

安装方法

能做什么

Agent-first directory for Indians from India in the USA — restaurants, temples, events & more.

作者提供的原文

  • 连接方式 在云端运行
  • 账号或密钥 无需密钥
  • 分类 旅行、地图与天气

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度0/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度12/1230 天内有发布或代码更新得满分
仍在响应0/8上次检查时云端端点有响应
使用分12/100

质量: 基础检查通过 2/5 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

通过 2/5 项检查 · 在你的电脑上运行

我们隐藏了部分命令

通过地址连接:检查时服务器地址没有响应

还没有通过检查的安装方式。请看作者的说明,或选择同类的其他服务器 · 作者的安装说明 · 同类的其他服务器

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

Claude 暂时无法连接 Namaste America

还没有通过检查的安装方式。请看作者的说明,或选择同类的其他服务器

ChatGPT 暂时无法连接 Namaste America

还没有通过检查的安装方式。请看作者的说明,或选择同类的其他服务器

你可以改用这些方式

B · 旅行、地图与天气 类中能连接 ChatGPT 的其他服务器

从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的

Claude Code 暂时无法连接 Namaste America

还没有通过检查的安装方式。请看作者的说明,或选择同类的其他服务器

Cursor 暂时无法连接 Namaste America

还没有通过检查的安装方式。请看作者的说明,或选择同类的其他服务器

VS Code 暂时无法连接 Namaste America

还没有通过检查的安装方式。请看作者的说明,或选择同类的其他服务器

还没有通过检查的安装方式。请看作者的说明,或选择同类的其他服务器

卡住了?问问正在用 Namaste America 的人💬 讨论 →

一览

每周下载量i
不在 npm/PyPI 上
已验证域名
✓ namasteamerica.us
许可证i
未注明许可证
连接方式
在云端运行
传输方式
streamable-http
最新版本i
0.1.0
发布到注册中心i
2026年7月8日
代码最后更新i
2026年11月16日
最近检查
2026年11月16日
作者
manvigallc007-spec
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

GooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月16日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • get_indian_restaurants

    Find Indian restaurants by location and/or filters. Provide either a point (`lat`+`lng`, optionally `radius_miles`) or `city`/`state`. Optional filters: `region_tag` (e.g. "Gujarati", "South Indian"), `dietary_tags` (any of "vegetarian", "vegan", "halal", "jain"), `tag` (a keywor

  • get_indian_movies_in_theaters

    List Indian-language movies currently playing in US theaters (Hindi, Telugu, Tamil, Malayalam, Kannada, Punjabi, Bengali, Marathi, Gujarati). Optional `language` filters to one (e.g. "Telugu"). Each movie includes `title`, `language`, `poster_url`, `overview`, `release_date`, `ge

  • search_h1b_sponsors

    Search US employers that sponsor H-1B visas — the visa most Indians-from-India use to work in the USA. Filter by employer name (`query`) and/or worksite `state` (2-letter). Ranked by number of certified Labor Condition Applications. Each result has `certified` (count), `median_wa

  • get_restaurant_details

    Fetch the full canonical record for one restaurant, plus its version history.

  • search_restaurants_by_text

    Free-text search over restaurant name/cuisine/region, ranked by relevance. Optionally constrain to a `city`/`state`. Featured listings are surfaced first. Use `offset` to page further (the response's `has_more` says whether another page exists).

  • submit_correction

    Propose a correction to a listing field (agents/users reporting bad data). `vertical` is the category key (default 'restaurants'); `listing_id` is the id from that category's get_/search_ tools. Correctable restaurant fields: phone, email, website, menu_url, address_full, city, s

  • submit_review

    Submit a community review (1-5 star rating + optional text) for a listing. `vertical` is the category key (restaurants, temples, groceries, professionals, salons, apparel, sweets, studios, services, community, legal, education, realestate, finance) and `listing_id` is the id retu

  • get_reviews

    Published community reviews for a listing (newest first) + its rolled-up community rating. The community rating is first-party (visitor-submitted) and is separate from any web-harvested `rating` returned by the get_/search_ tools. Each review includes the business owner's public

  • get_indian_temples

    Find Indian-American temples (Hindu/Sikh/Jain places of worship). Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `religion` ("hindu", "sikh", "jain"), `denomination` (e.g. "swaminarayan"), `tag`, or `open_now`. Records include description, dei

  • get_temple_details

    Full canonical record for one temple, plus its version history.

  • search_temples_by_text

    Free-text/semantic search over temples (name/deity/denomination/region).

  • get_indian_groceries

    Find Indian grocery stores (desi groceries / supermarkets). Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Optional `region_tag` (e.g. "Gujarati"), `tag` (e.g. "spices", "halal"), `open_now`. Records include description, store type, tags, hours, region

  • get_grocery_details

    Full canonical record for one grocery store, plus its version history.

  • search_groceries_by_text

    Free-text/semantic search over Indian grocery stores (name/region/store type).

  • get_indian_professionals

    Find Indian-American healthcare professionals (doctors, dentists, clinics, pharmacies). Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `profession_type` ("doctors", "dentist", "clinic", "pharmacy"), `speciality` (e.g. "pediatrics", "cardiology

  • get_professional_details

    Full canonical record for one professional/practice, plus its version history.

  • search_professionals_by_text

    Free-text/semantic search over Indian-American healthcare professionals.

  • get_indian_salons

    Find Indian beauty salons (threading, henna/mehndi, hair, bridal). Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `tag` (e.g. "threading", "henna", "bridal") or `open_now`. Records include description, services (tags), hours and an `open_now`

  • get_salon_details

    Full canonical record for one salon, plus its version history.

  • search_salons_by_text

    Free-text/semantic search over Indian beauty salons.

  • get_indian_events

    Find upcoming Indian-American community events (festivals, garba, concerts, puja). Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `category` ("festival", "garba", "concert", "puja", …) or `tag` ("diwali", "holi", …). Returns UPCOMING events by

  • get_event_details

    Full canonical record for one event, plus its version history.

  • search_events_by_text

    Free-text/semantic search over Indian-American events (incl. past, for history). `offset` pages.

  • get_indian_apparel

    Find Indian apparel & jewelry stores (sarees, lehengas, ethnic wear, gold jewelers). Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `tag` (e.g. "saree", "bridal", "gold", "jewelry", "tailoring") or `open_now`.

  • get_apparel_details

    Full canonical record for one apparel/jewelry store, plus its version history.

  • search_apparel_by_text

    Free-text/semantic search over Indian apparel & jewelry stores.

  • get_indian_sweets

    Find Indian sweets shops (mithai) & bakeries. Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `tag` (e.g. "mithai", "jalebi", "bakery", "eggless") or `open_now`.

  • get_sweets_details

    Full canonical record for one sweets shop / bakery, plus its version history.

  • search_sweets_by_text

    Free-text/semantic search over Indian sweets shops & bakeries.

  • get_indian_studios

    Find Indian yoga & cultural studios (yoga, classical dance, music, language classes). Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `tag` (e.g. "yoga", "bharatanatyam", "kathak", "tabla", "carnatic") or `open_now`.

  • get_studio_details

    Full canonical record for one studio, plus its version history.

  • search_studios_by_text

    Free-text/semantic search over Indian yoga/dance/music studios.

  • get_indian_services

    Find Indian community services (money transfer/remittance, banks, immigration/visa, travel agents, tax/insurance). Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `tag` (e.g. "money-transfer", "immigration", "travel", "tax") or `open_now`.

  • get_service_details

    Full canonical record for one service business, plus its version history.

  • search_services_by_text

    Free-text/semantic search over Indian community services.

  • get_indian_community

    Find Indian community organizations & cultural associations (regional samaj/sangam, cultural centers, Indo-American associations). Provide a point (`lat`+`lng`) or `city`/`state`. Filter by `tag` (e.g. a region like "telugu", "gujarati", or "association"/"cultural_center").

  • get_community_details

    Full canonical record for one community organization, plus its version history.

  • search_community_by_text

    Free-text/semantic search over Indian community organizations & associations.

  • get_indian_legal

    Find Indian-American immigration attorneys & law firms. Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `tag` (e.g. "immigration").

  • get_legal_details

    Full canonical record for one immigration/legal listing, plus its version history.

  • search_legal_by_text

    Free-text/semantic search over Indian-American immigration attorneys & law firms.

  • get_indian_education

    Find Indian-American education & tutoring (heritage/language schools, Bal Vihar, coaching). Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `tag` (e.g. "language_school", "heritage", "tutoring").

  • get_education_details

    Full canonical record for one education/tutoring listing, plus its version history.

  • search_education_by_text

    Free-text/semantic search over Indian-American education & tutoring.

  • get_indian_realestate

    Find Indian-American realtors & real-estate agencies. Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `tag` (e.g. "agency", "mortgage").

  • get_realestate_details

    Full canonical record for one real-estate listing, plus its version history.

  • search_realestate_by_text

    Free-text/semantic search over Indian-American realtors & real-estate agencies.

  • get_indian_finance

    Find Indian-American CPAs, tax preparers & financial advisors. Provide a point (`lat`+`lng`, optional `radius_miles`) or `city`/`state`. Filter by `tag` (e.g. "cpa", "tax", "financial_advisor").

  • get_finance_details

    Full canonical record for one finance/tax listing, plus its version history.

  • search_finance_by_text

    Free-text/semantic search over Indian-American CPAs, tax preparers & financial advisors.

  • search_all

    Search across ALL Indian-American verticals at once — restaurants, temples, groceries, healthcare professionals, beauty salons, events, apparel & jewelry, sweets & bakeries, yoga/dance studios, and community services. Use for broad queries like "Indian things near me in Edison NJ

  • get_festival_dates

    Upcoming Indian & South-Asian festival dates for planning in the USA. With no `query`, returns the next `limit` festivals soonest-first. With a `query` (e.g. "Diwali", "when is holi"), returns the single soonest matching festival. Each item has name, date (ISO), days_until, emoji

  • search_knowledge

    Grounded answers from the Namaste America knowledge base — culture, festivals, visa/H-1B, tax, banking, and newcomer/settling-in guides for Indians from India living in the USA. Returns the top matching passages, each with the source document's title + url so you can cite it. Opt

  • submit_listing

    Submit a new Indian-American business/listing for REVIEW — it does NOT go live automatically. `vertical` is the category key (restaurants, temples, groceries, professionals, salons, apparel, sweets, studios, services, community, legal, education, realestate, finance — not events,

  • get_movie_details

    Full details for one Indian movie (the id from get_indian_movies_in_theaters). Returns the movie record (title, language, overview, release_date, genres, poster_url, ...) or {'error': 'not_found'}. Movie data from TMDB; this product uses the TMDB API but is not endorsed or certif

  • get_h1b_sponsor_details

    Full details for one H-1B sponsor (the id from search_h1b_sponsors). Returns the sponsor record (employer, certified counts, wages, top titles/states/cities, ...) or {'error': 'not_found'}. Aggregated from U.S. Department of Labor LCA disclosure data.

  • search_community_questions

    Search the Namaste America community Q&A — real questions Indians in the USA ask and answer ("Telugu-speaking pediatrician in Plano?", "best sweets for Diwali in Edison?"). Returns published questions matching the query, most-answered first, each with a `slug` you can pass to get

  • get_community_answers

    A community question + its published answers (Dost's AI answer first, then community answers by upvotes). `slug` comes from search_community_questions. Returns the question with an `answers` list, or {'error': 'not_found'}.

  • get_today_highlights

    What's happening in Indian America today, optionally for a city + languages — the upcoming festival (+ approximate tithi), soonest events nearby, Indian movies in theaters, places newly added in the city, a culture/immigration nugget, and trending community questions. `languages`

  • get_offers

    Live offers & announcements posted by Indian-American business owners (e.g. "20% off thalis this week", "new weekend Garba class"), optionally filtered by city/state/vertical. Returns current, non-expired owner posts with the listing they belong to. Great for "any deals near me t

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日

  • ! 注意

    作者与仓库一致

    发布者(namasteamerica.us)不是仓库所有者(manvigallc007-spec);可能是其他人代为上架的

  • ✓ 通过

    仍在维护

    代码最后更新于4天前

  • ✕ 未通过

    有许可证

    仓库中没有找到许可证文件

  • ✕ 未通过

    端点有响应

    我们检查时,6 秒内没有响应

  • – 不适用

    使用 OAuth 登录

    我们检查时,6 秒内没有响应

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 60 个工具描述,未发现针对 AI 的隐藏指令

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/us-namasteamerica-namaste-america.svg)](https://mcp.popnx.com/en/servers/us-namasteamerica-namaste-america)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“旅行、地图与天气”中的其他服务器比较i

  • 星标数多于此分类中其他 2052 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 2052 个服务器的 12% 更新
  • 基础检查结果等于或优于此分类中其他 2052 个服务器的 7%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Namaste America 安全吗?

它在 5 项适用的基础检查中通过了 2 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。

它还在维护吗?

GitHub 仓库最后更新于4天前,最新版本(0.1.0)于4个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:Mu, Award Travel Finder, Killbottleneck, Gondola Award Travel Search, Whimsical

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Mu

News, web search, mail, markets, weather, places, files, calendar, contacts. 67 tools, one endpoint.

作者:micro正在增长★ 4414个月前更新

在云端运行✓ micro.mu

Killbottleneck

Free-to-self-host goal and process maps for humans and AI agents, with REST API and MCP.

作者:tengolabs起步阶段↓ 328/周★ 1413天前更新

在你的电脑上运行✓ 服务方 · killbottleneck.com

Whimsical

Create and edit flowcharts, mind maps, wireframes, and docs in Whimsical, or search your workspace.

作者:WhimsicalCode起步阶段★ 112个月前更新

在云端运行✓ 服务方 · whimsical.com
与相似项目对比
本项
Namaste America
MuAward Travel FinderKillbottleneckGondola Award Travel SearchWhimsical
运行位置在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装需要安装在电脑上在云端运行,无需安装在云端运行,无需安装
需要密钥否否否是否否
可在 Claude 中按 + 添加否否否否否是
基础检查2/54/43/33/34/44/4
许可证–AGPL-3.0MITMITMITMIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Indian–American Diaspora MCP Server

Agent-first, agent-only data layer for the Indian-American diaspora. Phase 1: Indian restaurants (USA). This repo is the walking skeleton from the architecture blueprint:

  • MCP server exposing restaurant capabilities (get_indian_restaurants, get_restaurant_details, search_restaurants_by_text, find_unclaimed_restaurants, draft_claim_outreach, submit_correction), temple capabilities (get_indian_temples, get_temple_details, search_temples_by_text) and grocery capabilities (get_indian_groceries, get_grocery_details, search_groceries_by_text) professional capabilities (get_indian_professionals, …), salon capabilities (get_indian_salons, …), and a cross-vertical `search_all` that searches every vertical at once (each result tagged with its vertical).
  • Data pipeline: scrape → raw → clean/enrich/score → approval queue → canonical table → versioning.
  • One real scraper: OpenStreetMap Overpass (public, ODbL-licensed, no login, ToS-safe).
  • Storage: PostgreSQL (+ pgvector for future embedding search) via Docker Compose.

Connect (live MCP server)

The hosted server is remote (no install) over streamable‑HTTP:

  • Endpoint: https://namasteamerica.us/mcp (transport: streamable-http, auth: none, read‑only)
  • Descriptor: https://namasteamerica.us/.well-known/mcp.json · Docs: https://namasteamerica.us/for-agents
{ "mcpServers": { "namaste-america": { "type": "streamable-http", "url": "https://namasteamerica.us/mcp" } } }

Tools (per vertical: restaurants, temples, groceries, professionals, salons, events, apparel, sweets, studios, services, community, legal, education, real estate, finance): get_indian_ , search_ _by_text, get_ _details, and a cross‑vertical `search_all`. Each result is JSON with address, geo, hours, contact, ratings, and languages.

Publishing to the official MCP registry: the manifest is server.json (namespace

us.namasteamerica, verified via DNS). Install the CLI (mcp-publisher), authenticate the domain

(mcp-publisher login dns --domain namasteamerica.us, then add the TXT record it prints), and run

mcp-publisher publish.

Architecture (Phase 1)

 OSM Overpass ──▶ restaurant_raw ──▶ clean()+score() ──▶ approval_queue ──▶ restaurants

(scraper) (JSONB) (pipeline) (high-risk only) (canonical) │ ▼ restaurant_versions │ ▼ MCP tools (FastMCP)

Low-risk new inserts are auto-applied (configurable); updates to claimed/featured listings are routed to the human approval queue.

Quick start

Requires Docker Desktop and Python 3.11+.

# 1. Start Postgres (with pgvector)

docker compose up -d

2. Create a virtualenv and install

python -m venv .venv .\.venv\Scripts\Activate.ps1 pip install -e .

3. Configure env

copy .env.example .env # default DATABASE_URL already points at the docker container

4. Initialise the schema

python -m indo_usa_mcp.cli init-db

5. Scrape one metro from OpenStreetMap, then process raw -> canonical

python -m indo_usa_mcp.cli scrape --metro bay_area python -m indo_usa_mcp.cli process

6. Inspect

python -m indo_usa_mcp.cli stats

7. Run the MCP server (stdio transport)

python -m indo_usa_mcp.server

CLI

CommandPurpose
init-dbApply SQL migrations (extensions, tables, indexes).
scrape --metro Run the OSM scraper for a metro bbox into restaurant_raw.
processClean/score unprocessed raw rows; auto-apply low-risk, queue high-risk.
approvalsList pending approval-queue items.
approve / reject Resolve an approval item.
outreach [--limit N]Draft claim outreach for unclaimed restaurants (creates claim links + messages).
verify-claim Owner-side: verify a claim token and take ownership.
agentsList the registered autonomous agents.
agent Run one agent now (audited in agent_runs).
agents-loop [--once]Run the scheduler (worker loop over due agents).
query [--city/--text/--lat --lng/--id/...]Call the MCP tool functions from the terminal.
seedLoad fictional seed restaurants for local testing (no scrape needed).
enrichBackfill region/dietary cultural tags on under-tagged restaurants.
deactivate-stale [--days 60]Mark unclaimed listings not seen recently as inactive.
approval-digestHuman-readable summary of the pending approval queue.
feedback --id N --field F --value VSubmit a field correction (applied by the feedback agent).
scrape --metro usaNationwide sweep (occasional; slower than a single metro).
`feature --id N [--days 30 \--permanent]`Mark a paid featured listing.
unfeature --id NRemove a featured listing.
backfill-embeddings [--all](Re)compute embeddings for canonical rows.
statsRow counts and coverage summary.

Monetization & delivery

  • Featured listings (feature/unfeature) — a paid tier; effectively-featured rows (flagged and within their featured_until window) surface first in every tool result.
  • Stripe checkout (optional) — claimed owners get a "Get Featured" button → Stripe Checkout → a signature-verified webhook (/stripe/webhook) auto-features them. Disabled until STRIPE_SECRET_KEY is set (then it's pay-per-sale, no monthly fee). See DEPLOY.md.
  • Outreach email delivery — optional and zero-cost: set Gmail SMTP + an app password in .env (see .env.example) and the Outreach Agent will auto-send claim emails to restaurants that have a public email; otherwise it stays draft-only.
  • Enrichment agent — strengthens the cultural "data moat" by inferring region/dietary tags from restaurant names (free, keyword-based).

Coverage spans 15 metros (Bay Area, NYC/NJ, Dallas, Houston, Chicago, LA, Seattle, Atlanta, Phoenix, Austin, Boston, Philadelphia, Raleigh, Detroit, Central NJ) plus an on-demand nationwide sweep (scrape --metro usa).

WhatsApp outreach is delivered as free click-to-send `wa.me` links (message pre-filled); true auto-send WhatsApp needs a paid API and is intentionally not used.

Trying it without a live scrape

python -m indo_usa_mcp.cli init-db

python -m indo_usa_mcp.cli seed # 12 fictional restaurants across the 5 metros python -m indo_usa_mcp.cli stats

Then exercise the MCP tools (e.g. get_indian_restaurants near the Bay Area, or search_restaurants_by_text "vegetarian dosa").

Search quality (for LLM agents)

Records are optimized for agent retrieval:

  • Natural-language `description` per record (e.g. *"Saffron House is a Gujarati Indian restaurant in Edison, NJ. Offers vegetarian, jain options. Price: $$."*) — generated from the structured fields, returned to agents, and used as the text that gets embedded.
  • Reverse-geocoded location — missing city/state are filled offline from coordinates (reverse_geocoder), so "near me / in " queries work for every record.
  • Keyword + attribute `tags` (e.g. biryani, dosa, halal, delivery, takeout, outdoor-seating, wheelchair-accessible, wifi, cards-accepted, organic) — derived from names and rich OSM attributes; agents filter with tag=..., and they boost embedding recall + appear in the description ("Amenities: …").
  • `open_now` — opening_hours are parsed into structured per-day intervals; each result carries an open_now flag (true/false/null) and the tools accept an open_now=true filter, enabling "what's open near me right now".
  • Dedup-merge — the admin Quality view lists duplicate groups with a one-click merge (fills the keeper's empty fields, soft-deletes the rest).

search_*_by_text ranks by embedding cosine distance (pgvector <=>), falling back to trigram. Providers (EMBEDDING_PROVIDER):

  • `hashing` (default) — feature-hashing, zero extra deps; lexical.
  • `fastembed` (recommended, prod default) — real semantic embeddings via BAAI/bge-small-en-v1.5 (384-dim, ONNX, no torch). The Docker image includes it and the prod compose defaults EMBEDDING_PROVIDER=fastembed; after deploying run python -m indo_usa_mcp.cli enhance-data once to re-embed existing rows. Set EMBEDDING_PROVIDER=hashing if the VPS is RAM-constrained.
  • `sentence_transformers` — all-MiniLM-L6-v2 (heavier, pulls torch).
  • `none` — trigram only.

enhance-data (re)generates descriptions, fills geocoding, and re-embeds existing rows — run it after enabling a new embedder. New records get all of this automatically on ingest.

Outreach & claiming (blueprint §7)

# Draft claim messages + single-use claim links for unclaimed restaurants

python -m indo_usa_mcp.cli outreach --limit 10

Later, an owner verifies their claim token (normally via the claim web page)

python -m indo_usa_mcp.cli verify-claim --email owner@example.com

After claiming, owners get an edit page (/manage?token=...) to update their phone, hours, menu, price, dietary tags, etc. — changes go live immediately and are protected from scraper overwrites (scraper updates to claimed listings route to the approval queue). Stale listings not re-seen for 60 days are auto-deactivated (is_active=false) and reactivated if they reappear in a later scrape.

The Outreach Agent finds unclaimed restaurants (skipping anything with an open claim or contacted within OUTREACH_COOLDOWN_DAYS), creates a single-use claim token + link, and drafts an honest, opt-out-friendly message per restaurant. Messages are not auto-sent — delivery needs channel integrations, and chains / featured / high-value targets are flagged requires_human. Once an owner verifies, restaurants.is_claimed flips to true and future scraper updates to that listing are routed to the approval queue. Agents can drive this via the find_unclaimed_restaurants and draft_claim_outreach MCP tools.

Autonomous agents (blueprint §6)

Each agent wraps a pipeline step, is idempotent, and writes a full audit row to agent_runs (errors captured, never half-written canonical data).

AgentDoes
discoveryReports metro coverage and proposes scrape targets.
scraperRuns every scraper across every metro into restaurant_raw.
cleanerProcesses raw → canonical via clean/score/approval.
outreachDrafts claim outreach for eligible unclaimed restaurants.
monitoringDetects anomalies (backlogs, scraper failures, stale data) → agent_alerts.
submissionSubmits the MCP to directories (manual stub for now).
python -m indo_usa_mcp.cli agents              # list agents

python -m indo_usa_mcp.cli agent scraper # run one, audited python -m indo_usa_mcp.cli agents-loop --once # one scheduler pass (scrape→clean→monitor…) python -m indo_usa_mcp.agents.scheduler # long-lived scheduler (VPS worker)

Data sources

Two independent public scrapers feed the pipeline: osm_overpass (OpenStreetMap, ODbL) and wikidata (Wikidata SPARQL, CC0). Pick one with scrape --source ; the Scraper Agent runs both.

Phase 2: Temples vertical

An independent vertical (Hindu/Sikh/Jain places of worship) sharing the same pipeline, agents, embeddings and deployment — per the blueprint's "independent verticals, shared

只显示了开头部分;其余内容请在仓库中阅读