India API

io.github.dharunashokkumar由 GitHub 账号 dharunashokkumar 发布v1.1.35更新于 Oct 25, 2026

Free Indian data and AI: pincode, IFSC, GSTIN, holidays, GST invoice, OCR, translation. No key.

已验证Streamable HTTP可网页运行位置与生活开发者工具AI 与机器学习

概览

AI 生成的概览

一个免费、无需密钥的远程 MCP 服务器,提供印度参考数据、格式校验,以及翻译、OCR、文档生成等 AI 工具。

可以做什么
查询印度参考数据:邮编与邮局、IFSC 银行网点、RTO 代码、节假日与工作日、HSN 编码、机场、火车站、选区,以及 NSE/BSE 公司信息与标志。执行 IP、DNS、邮件、whois、TLS 和 IPv6 检查,获取网站图标。生成 UPI 支付链接、二维码和条形码,进行数字转文字、标识符格式校验和假测试数据生成。提供文本分块、向量嵌入、重排序、内容审核、音译、翻译、语音转文字、文字转语音、OCR 和条码读取。处理图像与 PDF,生成 GST 发票和 Typst PDF,制作代码图与链接预览图,并转换泰米尔语旧编码。
适用场景
当助手需要印度地址、银行、税务、节假日、公司或交通信息时适用;也适合在无需注册 API 密钥的情况下生成发票、二维码、图片、PDF,或使用印度语言翻译、音译、OCR 和语音工具。
运行要求
远程 Streamable HTTP 端点;无需身份验证、API 密钥或注册。需要能访问该服务的网络。每个客户端每分钟 600 次请求额度,计算量大的操作消耗更多。
安装前请注意
格式校验只确认结构,不确认标识符是否真实签发。UPI 支付链接仅生成,不会与银行核实。上传的文件会发送到第三方服务,不过 README 称响应后即删除。部分印地语文字转语音声音仅限非商业用途,公司标志为其所有者商标。

安装

在 SourceWeft 中

  1. 打开 控制台中的 India API,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.dharunashokkumar%2Findia-api/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "india-api": {
      "type": "http",
      "url": "https://api.dharun.dev/mcp"
    }
  }
}

README

India API

Free, open source APIs for Indian data. Pincodes, IFSC and bank branches, GSTIN and PAN checks, bank and market holidays, RTO codes, company logos, UPI QR codes, numbers in lakh and crore, GST invoices as PDF, OCR in Indian languages, PDF and image tools, translation, speech to text and text to speech, and more: 44 APIs behind one consistent JSON shape. No API key, no sign-up, open CORS, and an MCP server so AI assistants can use it too.

[CI] [OpenSSF Scorecard] [OpenSSF Best Practices] [Licence: AGPL-3.0]

Documentation: api.dharun.dev · API reference · Guides · Use with AI · OpenAPI · llms.txt

bash
curl https://api.dharun.dev/v1/pincode/637001
json
{  "data": { "pincode": "637001", "district": "Namakkal", "stateCode": "TN", "state": "Tamil Nadu", "offices": [ ... ] },  "meta": { "source": { "name": "...", "licence": "...", "attribution": "..." } }}

APIs

Each name links to its page, with every parameter, a real response and code in curl, JavaScript and Python.

APIExampleWhat you get
Company logos/v1/logos/TCS, /v1/companies/RELIANCESVG or PNG logo of an NSE or BSE listed company, REITs and InvITs included; sector, ISIN, market cap, indexes; old tickers still work
Pincodes/v1/pincode/637001, /v1/pincode/near?lat=&lng=Post offices, district, state, coordinates; pincodes near a point
IFSC and banks/v1/ifsc/SBIN0000001, /v1/banks?q=graminBank, branch, address, MICR, payment systems; banks and their codes by name
RTO codes/v1/rto/TN-28Transport office for a vehicle registration
Holidays/v1/holidays/2026?type=marketBank, central government and stock market holidays
Working days/v1/working-days/2026-01-16?calendar=bank&state=TNWorking day or not, the next one, N working days ahead, T+1 settlement dates; whether NSE is open
HSN and SAC/v1/hsn/0902, /v1/hsn?q=teaTariff codes with descriptions and their chapter
Mutual funds/v1/mutual-funds/122639Latest NAV of a scheme, search by name or fund house
Railway stations/v1/stations/MASStation name, zone, state
Airports/v1/airports/MAAIATA and ICAO codes, city, coordinates
Phone numbers/v1/phone/9500112345Valid or not, mobile or landline, original operator and circle
Constituencies/v1/constituency?pincode=637001Assembly and parliamentary constituency for a place
Panchang/v1/panchang/2026-01-14?pincode=600001Tithi, nakshatra, yoga, karana, sunrise, Rahu kalam, Tamil month
Sun and moon/v1/sun-moon/today?pincode=600001Sunrise, sunset, twilight, moonrise, moon phase and illumination
Satellite passes/v1/sat-pass?sat=ISS&pincode=600001When the ISS or an amateur radio satellite passes over, and whether it can be seen
HF propagation/v1/propagationSolar flux, K and A index, NOAA scales, and a day and night rating per band
Thirukkural/v1/thirukkural/1Couplet, transliteration, two English translations; search and random
Transliteration/v1/transliterate?to=tamil&text=..., /v1/transliterate/suggest?lang=ta&text=vanakkamBetween nine Indian scripts, ISO 15919, IAST and ASCII; Roman typing to 21 Indian scripts with a model
Translation/v1/translate?from=en&to=ta&text=...Between English and 22 Indian languages with IndicTrans2
Embeddings and reranking/v1/embed?text=..., POST /v1/rerankMultilingual vectors for semantic search, and a reranker to order results
Tamil legacy encodings/v1/tamil-font/convert?from=tscii&text=...TSCII text to Unicode and back
IP lookup/v1/ip/8.8.8.8, /v1/ipCountry, city and network of an address, or of the caller
Email check/v1/email/[email protected]Syntax, disposable domain, whether the domain takes mail
DNS check/v1/dns/example.com?type=MXRecords as several public resolvers see them
Traceroute from India/v1/mtr/example.comMTR-style path from a server in India: network, loss and latency per hop
Whois/v1/whois/example.co.in, /v1/whois/AS55836Registrar, dates, status and nameservers of a domain; holder and abuse contact of an IP network or AS number, through RDAP
TLS check/v1/tls/example.comCertificate validity, chain, days left, TLS versions and weak ciphers, as a list of problems
IPv6 check/v1/ipv6/example.comIPv6 addresses for the site, its nameservers and mail servers
HTTP probe from India/v1/probe?url=https://example.comDNS, connect, TLS and first-byte times from India, redirects, headers and the CDN edge city
Website icons/v1/icon/github.com?size=64Any site's icon as a square PNG, or an initials tile
QR, UPI QR and barcodes/v1/qr?text=hello, /v1/upi-qr?pa=shop@okaxis&am=250, POST /v1/barcode/readQR codes, UPI payment QR codes and links, barcodes; reading codes from a photo
GST invoicePOST /v1/invoiceA GST tax invoice PDF from JSON: CGST and SGST or IGST, HSN summary, amount in words, UPI QR
OCRPOST /v1/ocr?lang=eng+tamText from photos, scans and scanned PDFs in English and ten Indian languages
Image toolsPOST /v1/image/convert?format=webp&width=800Resize and convert (WebP, AVIF, HEIC in), remove backgrounds, perceptual hashes
PDF toolsPOST /v1/pdf/merge, /pages, /rotate, /compress, /text, /renderMerge, split, rotate, compress, read text, draw pages
Typst to PDF/v1/typst?text=...Typst documents to PDF or PNG, with Indian scripts
SpeechPOST /v1/stt, /v1/tts?text=...&voice=hi, POST /v1/audio/denoiseSpeech to text and subtitles with Whisper; text to speech in Hindi, Telugu, Malayalam and English; noise removal
Generated images/v1/og-image?title=HelloLink preview cards and code images, in ten scripts
Text tools/v1/text/chunk, /redact, /moderate, /tokens, /languageChunking for retrieval, PII and name redaction, moderation with Hinglish and Tanglish, token counts, language detection
Regex tester/v1/regex?pattern=...&text=...Every match with its groups, replacement, the pattern explained
Fake Indian data/v1/fake/companies?count=5Test people and companies with PAN and GSTIN that pass format checks
Number to words/v1/words/1,25,000?lang=taLakh and crore spelling in English, Hindi, Tamil
Format checks/v1/validate/gstin/27AAPFU0939F1ZVGSTIN, PAN and IFSC structure and check characters
States/v1/states/TNState codes, GST codes, vehicle prefixes

One shape everywhere

  • Every JSON response is { "data": ..., "meta": { ... } }. data is an object, or an array for list endpoints, which add meta.total, meta.limit and meta.offset.
  • meta.source names the dataset, its version, its licence and the credit it asks for.
  • Errors are { "error": { "code", "message" } } with a matching HTTP status.
  • Each client has an allowance of 600 requests a minute. A lookup costs 1; a request that takes real CPU work (image rendering, astronomy, live DNS) costs 10, a file upload 15, and a neural network job (speech, speech to text, translation, background removal, denoise) 30. Embeddings, reranking and moderation count as CPU work.
  • Text endpoints take ?text=, or a POST body as text/plain or JSON {"text": "..."}.
  • Image endpoints return the image itself, ready for an <img> tag; PDF and audio endpoints return the file.
  • File endpoints take a POST of the file as the body, or as multipart/form-data, up to 10 MB. Files are deleted when the answer is sent; nothing is kept.

Use it from AI assistants

One MCP server, one Agent Skill and one Claude Code plugin cover every API.

bash
# Claude Code: the MCP serverclaude mcp add --transport http india-api https://api.dharun.dev/mcp
# Claude Code: the plugin (skill and MCP server together)/plugin marketplace add dharunashokkumar/api.dharun.dev/plugin install india-api@dharun-dev
# Any agent that reads Agent Skills (Claude Code, Codex, Copilot, Cursor, Gemini CLI)npx skills add dharunashokkumar/api.dharun.dev
  • MCP server: https://api.dharun.dev/mcp, Streamable HTTP, stateless, no authentication. Each tool returns exactly what the matching REST endpoint returns. Setup for Claude, ChatGPT, VS Code, Cursor, Windsurf, Gemini CLI and Codex: api.dharun.dev/ai. In the MCP Registry as io.github.dharunashokkumar/india-api.
  • Agent Skill: skills/india-api.
  • Claude Code plugin: plugins/india-api, with the marketplace in .claude-plugin/marketplace.json.
  • For crawlers and agents: /llms.txt, /llms-full.txt, every page as Markdown (add .md or send Accept: text/markdown), /openapi.json, an MCP server card, an AI catalog and an API catalog under /.well-known/.

The skill, the plugin and server.json are generated from the catalog in internal/api/catalog.go; a test fails when the committed copies are out of date.

Licence

  • Calling the API puts no licence on your app.
  • The code is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0-only). If you run a modified copy as a service for others, you must offer them your changes.
  • Code examples, the guides' code, the Agent Skill and the Claude Code plugin are MIT-0: use them anywhere, no credit needed.
  • Data keeps the licence of its source (below); every response repeats the credit.
  • Third-party code and fonts compiled into the server keep their licences, such as the SGP4 code in internal/orbit (BSD-2-Clause) and the Noto fonts (OFL-1.1). The release bundle's NOTICES lists every one.
  • Company logos are trademarks of their owners.

Security and privacy

Report vulnerabilities privately: see SECURITY.md. Client IP addresses are never logged, and endpoints that take personal values never log their input; the full list is at api.dharun.dev/privacy. Each release carries a build provenance attestation:

bash
gh attestation verify dharun-api-linux-amd64.tar.gz --repo dharunashokkumar/api.dharun.dev

Contributing

Bug reports, corrections to data and requests for new APIs are welcome as issues. Pull requests are not accepted; see CONTRIBUTING.md.

Data sources

DatasetSourceLicenceRecords
PincodesAll India Pincode Directory, Department of Posts (data.gov.in)Government Open Data License - India157,125 post offices
IFSCrazorpay/ifsc, compiled from Reserve Bank of India and NPCI listsPublic domain, as stated by the publisher183,214 branches
RTO codesWikipedia, "List of Regional Transport Office districts in India"CC BY-SA 4.0 (shared under the same licence)1,361 codes
Bank holidaysReserve Bank of India holiday matrix, 34 regional officesOfficial publication2026
Central government holidaysDepartment of Personnel and Training memorandaOfficial publication2026, 2027
Market and clearing holidaysNational Stock Exchange of IndiaOfficial publication2026
HSN and SAC codesGST portal code list; the nomenclature is from the Customs Tariff Act, 1975 and GST notification 11/2017Statute22,614 codes
Mutual fund NAVAssociation of Mutual Funds in India, NAVAll.txtPublished daily by AMFI; credited14,375 schemes
Railway stationsWikipedia, "List of railway stations in India"CC BY-SA 4.0 (shared under the same licence)3,975 stations
AirportsOurAirportsPublic domain9,509 airports, 622 in India
Phone seriesWikipedia, "Mobile telephone numbering in India"CC BY-SA 4.0 (shared under the same licence)2,247 series
ConstituenciesDataMeet community mapsAssembly CC BY 2.5 India; parliamentary CC04,182 assembly, 543 parliamentary
Thirukkuraltk120404/thirukkural; translations by G.U. Pope and by Drew and LazarusPublic domain text; compilation Apache-2.01,330 couplets
IP addressesDB-IP LiteCC BY 4.0fetched by each server
Whois registriesIANA RDAP bootstrap registries (RFC 9224); each registration is fetched live from its registryCC0 1.01,201 top-level domains, refreshed weekly
Orbit elementsCelesTrak, from US Space Force data via Space-Track.org; only computed passes and positions are publishedNone stated; redistribution with credit allowed by USSPACECOMfetched by each server, 111 satellites
Space weatherNOAA Space Weather Prediction CenterPublic domain (US government work)fetched by each server, hourly
Speech voicesPiper voices, each trained on its own recordingsPer voice: public domain, CC BY 4.0, IIT Madras Indic TTS licence, or CC BY-NC-SA 4.0 (two Hindi voices, non-commercial)fetched by each server, 10 voices
Background removal modelIS-Net (Qin et al.), ONNX export by rembgApache-2.0fetched by each server
Embeddings and rerankingmultilingual-e5-small (Microsoft); bge-reranker-v2-m3 (BAAI)MIT; Apache-2.0fetched by each server
Speech recognitionWhisper small (OpenAI), through whisper.cppMITfetched by each server
TranslationIndicTrans2 distilled 200M (AI4Bharat)MITfetched by each server
Transliteration modelIndicXlit (AI4Bharat), converted to ONNX hereMITfetched by each server
Name detectionIndicNER (AI4Bharat); bert-base-NERMITfetched by each server
ModerationDetoxify multilingual (Unitary); Hinglish toxicity (Darel Philip, on L3Cube HingRoBERTa, CC BY 4.0); Tanglish offensive language (Sean Benhur)Apache-2.0; MIT; Apache-2.0fetched by each server
Disposable email domainsdisposable-email-domainsCC09,881 domains
Logos and company detailsCollected from TradingViewLogos are trademarks of the companies they identify5,599 companies, 5,354 with a logo

Exact versions, retrieval dates and checksums are in data/sources.json (the models: pinned by revision and checksum in internal/dataset/aimodels.go), and every response repeats the credit in meta.source. Models published only as PyTorch weights or in full precision were converted to ONNX and int8 by tools/models/convert.py and attached to the models-2026-10 release.

Known gaps:

  • State government holidays are not included. Bank holidays are per state, and they come from each state's own notification.
  • Andaman and Nicobar RTO codes are missing: the source article has no section for them.
  • The pincode file was fetched through a mirror because the government portal refuses scripted downloads. Its size matches the file the portal lists.
  • Railway stations come from a community list: some stations are missing and a few codes are out of date.
  • Assembly constituency boundaries pre-date the latest redrawing in six states; the response says so where it applies.
  • Phone operator and circle are the original allocation of a number series. A ported number keeps its series, so the current operator can differ.
  • Panchang timings are computed from Sun and Moon positions and can differ from a printed almanac by a minute or so.
  • Tamil legacy encodings: TSCII only so far; TAB, TAM and Bamini are planned.
  • Hindi and Tamil number words follow standard written forms, with Tamil compound numbers written as separate words. Corrections are welcome.

Run it locally

Requires Go 1.26 or newer.

bash
go run ./cmd/apidata build -resvg none    # build every dataset from data/ into seed/go run ./cmd/api                          # http://127.0.0.1:8080/go test ./...

PNG output (logos and generated images) is rendered by resvg; bash tools/fetch-resvg.sh <dir> downloads the pinned Linux build. Without it everything else works and PNG requests answer 501.

Configuration is by environment variable; see deploy/dharun-api.env.example. ROADMAP.md tracks what is built, what is planned and what was turned down.

Repository layout

text
cmd/api            the servercmd/apidata        data tool: build, import, refresh, statusinternal/api       routing, endpoints, the website, MCP, metricsinternal/api/guides      the guides, in Markdowninternal/api/templates   the Markdown forms of the pages and the skillinternal/dataset   one file per dataset: how it is built, fetched and checkedinternal/typeset   text shaping and the fonts for generated imagesinternal/panchang  almanac calculationsinternal/translit  transliteration between scriptsinternal/tamilfont Tamil 8-bit encodingsinternal/textkit   chunking, redaction, token counts, language detectioninternal/fake      test datainternal/words     number to wordsinternal/validate  GSTIN, PAN, IFSC and checksum rulesinternal/india     states and their codesdata/              one folder per dataset (logos included), and sources.jsonskills/            the Agent Skill (generated from the catalog)plugins/           the Claude Code plugin (generated); marketplace in .claude-plugin/server.json        the MCP Registry entry (generated)deploy/            systemd units, installer, self-updater, monitoringtools/             release build, smoke test, install test, resvg download, logo scraper

How data stays fresh

Each dataset is its own read-only SQLite file. A release carries a seed copy of every dataset, built from data/. On a server, apidata refresh runs hourly as a separate short-lived job: each dataset that a program can fetch (IFSC, RTO codes, bank and market holidays, HSN, mutual fund NAV, airports, stations, IP addresses, disposable domains) is downloaded when it is due, checked, and built into a new file in the server's own data directory. The API serves whichever copy is newer and picks up a new file without a restart. A deploy replaces the seeds and never touches the server's own copies.

Datasets that cannot be fetched by a program are updated by hand and ship with a push:

bash
go run ./cmd/apidata import pincode -file pincode.csv    # CSV saved from data.gov.inpython tools/scrape_logos.py --dry-run                   # logos: see new, renamed and delisted companiespython tools/scrape_logos.py                             # then download and write themgo run ./cmd/apidata status                              # which copy of each dataset is in use

Central government holidays are typed into data/holidays/central/<year>.json from the yearly memorandum, usually published in July for the following year.

Release and deploy

Deployment is pull-based: the server fetches releases, nothing connects in to it.

  1. Every push to main runs CI: tests, shell lint, a full release build, a smoke test of the bundle against the full datasets, and an install of it on a fresh Debian 13.
  2. When it passes, the bundle is published as release v1.1.<run number>.
  3. On the server, dharun-api-update.timer checks every 2 minutes. It downloads the new release, verifies the checksum, switches to it, and checks /healthz. If the new version does not come up, it switches back and marks that release as failed.
  4. When CI has finished, the Production workflow waits (up to 20 minutes) for the public /healthz to report the new version, then runs the smoke test's route checks against the live site. A release that was never installed, or was rolled back, fails the run. The run shows on GitHub as a deployment to production.

First-time setup on a Debian 12 or 13 machine or container, as root:

bash
tar -C deploy -cz . | ssh <host> 'mkdir -p /root/api-deploy && tar -xz -C /root/api-deploy && sh /root/api-deploy/install.sh'

The server is one static binary plus a database file per dataset. It runs as the unprivileged user dharun-api with a read-only filesystem, and uses about 35 MB of memory idle and about 150 MB under a burst. The updater runs as root and is only replaced by re-running install.sh. Restrict port 8080 to your proxy and port 9464 to Prometheus with a firewall.

Monitoring

  • :9464/metrics serves Prometheus metrics: requests by API and status, response times, logo lookups, memory, api_lifetime_requests_total, and for each dataset which copy is in use, how old it is and whether its last refresh worked.
  • :9464/stats serves the all-time totals as JSON. They are saved to disk and survive restarts.
  • deploy/monitoring/ has the Prometheus scrape job, alert rules (API down, a refresh that keeps failing, stale data) and a Grafana dashboard.
  • Every request is one JSON line on stdout: route, status, duration, what was looked up, country and user agent. Client IP addresses are not logged, and format checks log nothing about the value checked.

Trademark notice

Company logos and trademarks belong to their respective owners. This project is an index for discovery and convenience; review each company's brand rules before production use. To request removal of a logo, open an issue.

来源:README.md,提交 8f7bd6c

工具

80

search_companies

Search companies

Search Indian listed companies by ticker, earlier ticker, name, sector, industry, ISIN or index name (for example 'Nifty 50'). Returns details with logo URLs. Only companies listed today.

输入参数limitquery必填exchange

lookup_pincode

Lookup pincode

Look up an Indian pincode: its district, state and every post office that uses it.

输入参数pincode必填

search_post_offices

Search post offices

Find Indian post offices and their pincodes by the start of the office name, optionally within a state or district.

输入参数query必填statedistrict

lookup_ifsc

Lookup ifsc

Look up an Indian bank branch by its IFSC: bank, branch, address, MICR and supported payment systems.

输入参数ifsc必填

search_bank_branches

Search bank branches

Find branches of one Indian bank by state, city or text in the branch name or address. Needs the four-letter bank code; use search_banks to find it.

输入参数bank必填cityquerystate

search_banks

Search banks

Find Indian banks and their four-letter codes by name.

输入参数query必填

lookup_rto

Lookup rto

Find which Regional Transport Office an Indian vehicle registration belongs to. Accepts a code (TN-28) or a full number plate (TN28AB1234).

输入参数code必填

list_holidays

List holidays

List Indian holidays for a year: bank holidays, central government holidays, and stock market trading and clearing holidays. Filter by type, state or month.

输入参数typeyear必填monthstate

number_to_words

Number to words

Spell a number or rupee amount in words using the Indian system (lakh, crore), in English, Hindi or Tamil.

输入参数langstylenumber必填

validate_identifier

Validate identifier

Check the format of an Indian GSTIN, PAN or IFSC. Format only: it does not confirm the identifier was issued.

输入参数kind必填value必填

lookup_airport

Lookup airport

Look up an airport by IATA code (MAA) or ICAO code (VOMM): name, city, state, country, coordinates and whether it has scheduled flights.

输入参数code必填

search_airports

Search airports

Search airports by name or city, worldwide (those with IATA codes) and every Indian airfield and heliport. Filter by country (ISO code) or Indian state.

输入参数querystatecountry

find_constituency

Find constituency

Find the assembly (MLA) and parliamentary (MP, Lok Sabha) constituency of a place in India, by pincode or by latitude and longitude.

输入参数latlngpincode

check_dns

Check dns

Look up a domain's DNS records (A, AAAA, MX, TXT, NS, CNAME, CAA, SOA, SRV, or PTR for an IP) at Cloudflare, Google, Quad9 and OpenDNS at once, and say whether they agree.

输入参数name必填type

check_email_address

Check email address

Check an email address without contacting its mail server: valid form, disposable (throwaway) domain, free provider, role account, and whether the domain has mail servers.

输入参数email必填

make_fake_indian_data

Make fake indian data

Generate made-up Indian test data for building apps: people (name, gender, birth date, email, phone, PAN, address) or companies (name, PAN, GSTIN with a valid check character, address) or addresses, at real pincodes. Never real people.

输入参数kind必填seedcountstate

lookup_hsn_code

Lookup hsn code

Look up an Indian HSN code (goods) or SAC code (services) used in GST invoices: its description, the chapter and heading above it, and the codes below it. No GST rates.

输入参数code必填

search_hsn_codes

Search hsn codes

Find Indian HSN (goods) or SAC (services) codes by words of their description, such as 'green tea' or 'construction'.

输入参数kindquery必填

domain_icon

Domain icon

Get the icon of any website as a square PNG, from its favicon, Apple touch icon or web app manifest, redrawn at the size asked. A site without a usable icon gets an initials tile.

输入参数sizedomain必填

lookup_ip_address

Lookup ip address

Find the country, region (Indian state), city and network operator of a public IPv4 or IPv6 address.

输入参数ip必填

check_ipv6

Check ipv6

Check whether a domain is ready for IPv6, from DNS: IPv6 (AAAA) addresses for the site and www, for each nameserver and each mail server, with a plain list of what is missing. No connection is made over IPv6.

输入参数domain必填

translate_text

Translate text

Translate text between English and 22 Indian languages (Hindi, Tamil, Telugu, Kannada, Malayalam, Bengali, Marathi, Gujarati, Punjabi, Odia, Assamese, Urdu and more) with AI4Bharat's IndicTrans2. Between two Indian languages it goes through English. Up to 2,000 characters.

输入参数to必填from必填text必填

transliterate_roman_typing

Transliterate roman typing

Turn Indian-language words typed in Roman letters (vanakkam, namaste, kaise ho) into their own script, as phone keyboards do, with several guesses per word. Uses AI4Bharat's IndicXlit. Up to 60 words.

输入参数lang必填text必填count

moderate_text

Moderate text

Score a comment or message for abuse with three classifiers: general multilingual, Hinglish (Hindi in Roman letters, by kind: profanity, harassment, hate speech, caste, communal, regional, misogyny) and Tanglish (Tamil in Roman letters). Scores 0 to 1; a model's guess, not a decision.

输入参数text必填threshold

transcribe_audio

Transcribe audio

Speech to text with Whisper: the text of a recording (MP3, WAV, Ogg, M4A, WebM or video), with timed segments; about a hundred languages, Indian ones included. task=translate writes it in English. The first five minutes are heard.

输入参数file必填tasklanguage

rerank_documents

Rerank documents

Order documents by how well each answers a query, with the multilingual bge-reranker-v2-m3 cross-encoder (Indian languages and English). Returns scores from 0 to 1, best first.

输入参数topquery必填documents必填

make_gst_invoice

Make gst invoice

Make an Indian GST tax invoice as a PDF from seller, buyer and items. Works out each line's taxable value, CGST and SGST (or UTGST) within a state or IGST across states, the HSN-wise summary, rounding and the amount in words. format=json returns the worked-out amounts only.

输入参数formatinvoice必填

compile_typst

Compile typst

Compile a Typst document to PDF (or one page as PNG). Noto fonts for Latin and nine Indian scripts are available; packages and files are not.

输入参数pageformatsource必填

text_to_speech

Text to speech

Speak text aloud in Hindi, Telugu, Malayalam or English with Piper voices; returns MP3 audio. Write the text in its own script. Some Hindi voices are for non-commercial use only.

输入参数text必填speedvoice

read_text_in_image

Read text in image

OCR: read the text in a photo, scan or scanned PDF, in English and Indian languages (Hindi, Tamil, Telugu, Kannada, Malayalam, Bengali, Gujarati, Punjabi, Odia, Marathi).

输入参数file必填lang

read_barcodes

Read barcodes

Find and read every QR code and barcode (Data Matrix, Aztec, EAN, UPC, Code 128, Code 39, ITF, Codabar) in a picture.

输入参数file必填

make_qr_code

Make qr code

Make a QR code image (PNG) for any text or link.

输入参数bgfgeccsizetext必填

make_barcode

Make barcode

Make a barcode image (PNG): Code 128, Code 39, Code 93, EAN-13, EAN-8, ITF, Codabar, Data Matrix, PDF417 or Aztec.

输入参数sizetext必填type必填scaleheight

make_code_image

Make code image

Draw a code snippet as a PNG picture of an editor window with syntax colouring, for slides, posts and READMEs. Up to 150 lines of 140 characters.

输入参数code必填themetitlelanguage

make_social_preview_image

Make social preview image

Make a 1200 by 630 link preview (Open Graph) image as PNG from a title, with an optional subtitle, site name and tag. Latin and nine Indian scripts are set correctly. The same arguments always give the same picture.

输入参数tagsitethemetitle必填subtitle

chunk_text

Chunk text

Split a long document (plain text or Markdown) into readable chunks for retrieval (RAG): at headings, paragraphs, sentences and words in that order; Markdown chunks keep their heading path. Each chunk carries its character offsets.

输入参数sizetext必填formatoverlap

embed_texts

Embed texts

Turn texts into 384-number vectors with multilingual-e5-small (Indian languages and English), scaled to length 1 so a dot product is the cosine similarity. For storing in a vector database or comparing meaning; use rerank_documents to order a few passages for a question instead.

输入参数typetexts必填

convert_tamil_legacy_text

Convert tamil legacy text

Convert Tamil text in an old 8-bit encoding (TSCII), which shows as accented Latin letters such as ¾Á¢ú without its font, to Unicode Tamil, or Unicode back to it.

输入参数tofromtext必填

get_indian_states

Get indian states

List India's 28 states and 8 union territories, or get one, with its two-letter code, GST state code and vehicle registration prefixes.

输入参数state

convert_image

Convert image

Resize a picture or convert it (JPEG, PNG, WebP, AVIF, GIF, TIFF out; HEIC and AVIF read too). Turned upright, all metadata such as the GPS position removed.

输入参数fitfile必填widthformatheightquality

get_image_info

Get image info

Format, size, colour space, orientation and camera of a picture, and whether it carries EXIF data or a GPS position.

输入参数file必填

remove_image_background

Remove image background

Cut the subject out of a picture (a product, a person, an animal) and return it as a PNG with a transparent background, with the IS-Net model.

输入参数file必填format

hash_image

Hash image

Perceptual fingerprints of a picture (average, difference and DCT hashes) that stay nearly the same after resizing or recompression, for finding duplicates.

输入参数file必填

compare_images

Compare images

Compare two pictures by how they look: the bits by which their perceptual hashes differ, a score from 0 to 1, and whether they look like the same picture.

输入参数files必填

read_pdf_text

Read pdf text

Read the text of a PDF, page by page. needs_ocr is true when the pages are scanned pictures; send those to read_text_in_image.

输入参数file必填lastfirstlayout

get_pdf_info

Get pdf info

Page count, PDF version, title, author, dates and page sizes of a PDF, and whether it has forms, signatures or attachments.

输入参数file必填

render_pdf_page

Render pdf page

Draw one page of a PDF as a picture, for a preview.

输入参数file必填pagewidthformat

select_pdf_pages

Select pdf pages

Make a new PDF from some pages of one, in the order named: to pick, reorder or split pages.

输入参数file必填pages必填

rotate_pdf_pages

Rotate pdf pages

Turn the pages of a PDF clockwise by a multiple of 90 degrees.

输入参数file必填anglepages

compress_pdf

Compress pdf

Make a PDF smaller by removing duplicate fonts and images and packing its structure. Scanned PDFs shrink little.

输入参数file必填

merge_pdfs

Merge pdfs

Join PDFs into one, in the order given.

输入参数files必填

remove_audio_noise

Remove audio noise

Lower background noise (fans, traffic, hum) in a recording with DeepFilterNet; returns MP3. The first five minutes are cleaned.

输入参数file必填limit

traceroute_from_india

Traceroute from india

Trace the network path from a server in India to a host, MTR style: every hop with its address, name, network (AS) and country, packet loss and round-trip times. Shows how Indian networks reach a site.

输入参数vhost必填rounds

get_mutual_fund_nav

Get mutual fund nav

Get the latest NAV of an Indian mutual fund scheme by AMFI scheme code or ISIN, with its fund house, category, plan and option.

输入参数code必填

search_mutual_funds

Search mutual funds

Search Indian mutual fund schemes by name words, fund house or category, filtered by direct/regular plan and growth/IDCW option, with their latest NAVs.

输入参数planqueryoptionfund_house

get_panchang

Get panchang

Hindu almanac (panchang) for a date and place: tithi, nakshatra, yoga, karana with their end times, sunrise, sunset, moonrise, moonset, Rahu kalam, Yamagandam, Gulika kalam, Abhijit muhurta, Tamil month and day, lunar month, Shaka and Vikram years.

输入参数tzlatlngdate必填pincode

check_indian_phone_number

Check indian phone number

Check an Indian phone number's form and type (mobile, toll-free, fixed line), format it, and name the operator and telecom circle its series was originally given to.

输入参数number必填

probe_url_from_india

Probe url from india

Fetch a URL from a server in India and time it: DNS, connect, TLS, time to first byte and download, the HTTP status and version, every redirect, the response headers (cookie values hidden), the body's size and hash (never the body), and which CDN and edge city answered. Shows how fast a site is for visitors in India.

输入参数url必填rounds

get_hf_propagation

Get hf propagation

Current space weather from NOAA (solar flux, sunspot number, K and A indices, X-ray class, NOAA R/S/G scales) and a rule of thumb good/fair/poor rating of HF amateur radio bands by day and night.

无需输入参数。

test_regex

Test regex

Run a regular expression (JavaScript or RE2/Go syntax) against a text: every match with its groups and character offsets, an optional replacement, and a token by token explanation of the pattern.

输入参数text必填flagsflavorpattern必填replace

get_satellite_passes

Get satellite passes

When the ISS, the Chinese space station or an amateur radio satellite passes over a place in the next days: rise, highest point and set times with compass directions and elevations, and when the pass can be seen with the eye.

输入参数tzlatlngdayspincodesatellitevisible_onlymin_elevation

find_satellites

Find satellites

List or search the tracked space stations and amateur radio satellites, with catalogue numbers, orbital periods and inclinations.

输入参数groupquery

where_is_satellite

Where is satellite

Where a tracked satellite such as the ISS is right now: the point on Earth below it, its altitude and speed, and whether it is in sunlight.

输入参数satellite必填

lookup_railway_station

Lookup railway station

Look up an Indian Railways station by its code (MAS, NDLS): name, state, railway zone and elevation.

输入参数code必填

search_railway_stations

Search railway stations

Find Indian railway stations and their codes by name, state or railway zone.

输入参数zonequerystate

get_sun_and_moon

Get sun and moon

Sunrise, sunset, solar noon, day length, civil, nautical and astronomical twilight, moonrise, moonset, moon phase, illumination, age and the next new, first quarter, full and last quarter moons, for a date at an Indian pincode or any latitude and longitude.

输入参数tzlatlngdate必填pincode

count_tokens

Count tokens

Count the tokens a text uses for an OpenAI model or encoding (o200k_base for GPT-4o and later, cl100k_base for GPT-4).

输入参数text必填model

redact_indian_identifiers

Redact indian identifiers

Mask Aadhaar, PAN, GSTIN, card, phone, email, UPI ID, vehicle, voter ID, passport and IP numbers in a text, checking check digits where they exist.

输入参数text必填style

detect_language

Detect language

Detect the language and script of a text, including Indian languages.

输入参数text必填

get_thirukkural

Get thirukkural

Get a Thirukkural couplet by number (1-1330) in Tamil, with transliteration, English translations by G.U. Pope and by Drew and Lazarus, and its chapter.

输入参数number必填

search_thirukkural

Search thirukkural

Search the Thirukkural in Tamil or English, or list a chapter (1-133) or a paal (1 virtue, 2 wealth, 3 love).

输入参数paalquerychapter

check_tls

Check tls

Check a website's TLS certificate and setup on port 443, from India: whether the certificate is valid for the name and trusted, days until it expires, the chain as sent, issuer and key, which TLS versions (1.0 to 1.3) are accepted, the cipher and HTTP/2 offered, weak ciphers, and a plain list of problems.

输入参数host必填

transliterate_indian_text

Transliterate indian text

Rewrite text from one Indian script in another (Devanagari, Bengali, Gurmukhi, Gujarati, Odia, Tamil, Telugu, Kannada, Malayalam), or in Roman letters (ISO 15919, IAST, plain ASCII), or from ISO 15919 / IAST into a script. Spelling only, not translation.

输入参数to必填fromtext必填

whois_lookup

Whois lookup

Who registered a domain, IP network or AS number, through RDAP (the registries' replacement for whois): for a domain the registrar, registration and expiry dates, status, nameservers and DNSSEC; for an IP address or AS number the network, its holding organisation, country and abuse contact. Works for .in and .co.in. Personal contacts are never returned.

输入参数query必填

check_working_day

Check working day

Check whether a date is a working day in India for banks in a state, NSE trading, NSE settlement or central government offices; get the previous and next working days, or the date N working days away (T+1 settlement: calendar settlement, add 1).

输入参数adddate必填stateofficecalendar

count_working_days

Count working days

Count Indian working days between two dates (both included) for a calendar, and list each day off with its reason.

输入参数to必填from必填stateofficecalendar

indian_market_status

Indian market status

Is the Indian stock market (NSE equities) open now or at a given moment: session, reason if closed, and when it next opens.

输入参数at

find_post_offices_near

Find post offices near

Find Indian post offices and their pincodes near a latitude and longitude, nearest first.

输入参数lat必填lng必填radius

版本历史

3
  1. v1.1.35最新Oct 25, 2026
  2. v1.1.22Oct 15, 2026
  3. v1.1.18Oct 14, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分