mcp-bangladesh
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
@pipeworx/bangladesh
Bangladesh public data. First capability: the daily national dengue situation (hospital admissions and deaths, nationally and by division) from the Directorate General of Health Services.
Part of Pipeworx — an MCP gateway connecting AI agents to 1905+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
bd_dengue_report(date?)-- the DGHS daily dengue report: admissions and deaths in the last 24 hours, cumulative admissions, deaths, discharged and currently admitted since 1 January, nationally and (reports from late October 2026 on) for each of the eight divisions. Omitdatefor the latest; a date with no report returnsfound:falsewith the register range.bd_dengue_series(limit?)-- national figures for the last N reports (default 7, max 10), newest first.
Related MCP server: ARTPARK Public Data MCP Server
Auth
Keyless.
Data sources
Directorate General of Health Services (DGHS), Bangladesh -- the daily dengue press release of the Health Emergency Operation Centre and Control Room (public, no login).
Every call is read live; nothing is stored. Figures are hospital admissions reported to the control room, not laboratory-confirmed cases, and "year to date" counts from 1 January of the report year.
Traps worth knowing:
Reports up to about 25 October 2026 are an English dashboard layout with headline national figures only; later ones are a Bengali table with the division breakdown. Both are read; the layout is stated in the response when it is the headline-only form. Consecutive-day differences were checked against the 24-hour figure (for example 2026-09-30 to 2026-10-01: 79,620 + 1,978 = 81,598).
The Bengali report's text layer glues the six numbers of each row together. They are split back apart under two checks (admitted = discharged + deaths + currently admitted per row; the eight divisions sum to the national total). A report failing either check returns
parsed:falserather than a guess.A day with no report listed (gaps happen) returns
found:false.The Dhaka hospital-level pages of the report are not read (names in the text layer are unreliable).
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"bangladesh": {
"url": "https://gateway.pipeworx.io/bangladesh/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/bangladesh/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1905+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/bd_dengue_report \
-H 'Content-Type: application/json' \
-d '{"date":"2026-11-13"}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/bd_dengue_report. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Run it from npm
@pipeworx/mcp-bangladesh is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with npx, and it forwards every call to the same
https://gateway.pipeworx.io/bangladesh/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"bangladesh": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-bangladesh"]
}
}
}Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
"env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.
It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to
also list ask_pipeworx and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by
default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check
your Node version's documentation.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Bangladesh data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Real-time data API for AI Agents: stocks, weather, forex, logistics, search, scrape, news, IP.
Official daily Bangladesh agricultural market prices — unit-normalised, dated, citable.
660+ data tools for agents: TikTok, Douyin, Instagram, YouTube, X, weather, GitHub. Pay per call.
Official statistics for AI agents: Eurostat, World Bank, OECD, IMF and WHO data for 150+ countries.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides access to the World Health Organization's Global Health Observatory data, enabling AI assistants to search, retrieve, and analyze comprehensive health indicators, country statistics, disease burden data, and regional health trends through WHO's OData API.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to access and query ARTPARK's public health datasets including dengue epidemiology, livestock census, and FMD vaccination data through a structured 4-step workflow for data discovery and retrieval.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to query Kenya health facilities, maternal health indicators, immunization coverage, and disease surveillance data via the DHIS2 public API.3208 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceEnables querying ReliefWeb's humanitarian information service for situation reports, needs assessments, appeals, analyses, and curated disaster data, with tools to search, filter, and retrieve full reports.92 npmMIT