NTDeliver MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@NTDeliver MCP Server show me purchase orders for GSK in 2024"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
NTDeliver MCP Server
MCP server exposing NTDeliver purchase order and milestone data (1,729 POs, 2014-2027). Supports two transport modes: stdio (local) and HTTP/SSE (hosted, shared URL).
Quick start — local use
npm install
npm startAdd to Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"ntdeliver": {
"command": "node",
"args": ["/full/path/to/ntdeliver-mcp/src/index.js"]
}
}
}Related MCP server: mcp-hongkong-procurement
Shared access — one URL, no install required
Railway (recommended)
Push this repo to GitHub
Go to railway.app, create a project from the repo
Set env vars:
MCP_TRANSPORT=http,PORT=3000Railway detects the Dockerfile and deploys automatically
Your MCP URL: https://your-app.up.railway.app/sse
Render
Create a Web Service from the repo
Set env vars:
MCP_TRANSPORT=http,PORT=10000
Local HTTP mode (for testing)
MCP_TRANSPORT=http PORT=3000 node src/index.js
# Health check: curl http://localhost:3000/healthConnecting to a hosted server
Add to claude_desktop_config.json:
{
"mcpServers": {
"ntdeliver": {
"url": "https://your-app.up.railway.app/sse"
}
}
}Share that URL — anyone adds the same block and gets live NTDeliver data.
Tools
Tool | Description |
| Column names, row count, milestone list, known filter values, sample row |
| Filter POs by country, donor, drug, region, year, shipment mode |
| Full record + all milestones for a single PO number |
| Milestone dates and progress for matching POs |
| % of POs with each milestone recorded, across any filter set |
| PO counts and tablet totals grouped by donor/country/drug/region/year |
| All distinct values for any column |
| POs sorted by days until MDA, with optional max-days filter |
Known donors: GSK, Eisai, Merck USA, Merck KGaA, J&J Known drugs: ALB, DEC, IVM, MEB, PZQ, TCZ Known regions: AFRO, AMRO, EMRO, EURO, SEARO, WPRO Years: 2014-2027
Available Tools
8 toolsntd_days_to_mdaB
Find POs sorted by days until planned MDA. Optionally filter and/or limit by a maximum day threshold.
Inputs: drug, year, donor, country, +1 more.
ntd_get_milestonesC
Return milestone dates and progress for matching POs. Filter by PO number, country, donor, or drug.
Inputs: drug, donor, country, po_number.
ntd_get_poA
Get full details and all milestone dates for a single PO by PO number.
Inputs: po_number (required).
ntd_list_posA
List POs with optional filters. Returns key fields and milestone progress per PO. Donors: GSK, Eisai, Merck USA, Merck KGaA, J&J. Drugs: ALB, DEC, IVM, MEB, PZQ, TCZ. Regions: AFRO, AMRO, EMRO, EURO, SEARO, WPRO.
Inputs: drug, year, donor, limit, +3 more.
ntd_list_valuesB
All distinct values for any column. Useful for discovering valid filter values.
Inputs: field (required).
ntd_milestone_completionC
Aggregate milestone completion rates (% of POs with each milestone recorded). Filter by donor, country, drug, region, year.
Inputs: drug, year, donor, region, +1 more.
ntd_schemaA
Returns column names, row count, milestone column list, known filter values, and a sample row. Call this first.
Inputs: no named parameters.
ntd_summary_statsB
PO counts and total tablet quantities grouped by a field. group_by: donor | country | drug | region | year | mode.
Inputs: group_by.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose: schema discovery, listing/filtering POs, getting full details, milestone queries, aggregate statistics, value enumeration, and days-to-MDA analysis. No two tools overlap in function, making selection unambiguous.
All tools share the 'ntd_' prefix, but the naming convention is inconsistent: some use verb_noun ('list_pos', 'get_po', 'get_milestones', 'list_values'), while others are noun phrases ('schema', 'milestone_completion', 'summary_stats', 'days_to_mda'). This mixed pattern reduces predictability.
With eight tools, the server is well-scoped for a read-only data exploration API focused on NTD delivery POs. Each tool adds unique value without redundancy, and the count is appropriate for the domain's complexity.
The tool set covers all likely needs for querying an NTD delivery database: schema introspection, filtered lists, single-record details, milestone tracking, aggregate statistics, value discovery, and a specialized analytical query. There are no obvious gaps for a read-only server.
Maintenance
Related MCP Connectors
Access US federal award, recipient, agency, and spending analytics data from USAspending.gov.
Query USASpending.gov federal contract awards, grants, and government contractor recipients.
MCP access to the U.S. federal procurement graph: contracts, opportunities, entities, and more.
US federal contracting data: open solicitations, buying agencies, contractors, price history.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables querying international public procurement data, including government tenders, through the Open Contracting standard.627 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables querying Hong Kong Government procurement contracts awarded data through natural language, with no API key required.137 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables querying US defense contract awards of $7.5M+ from the daily press-release feed, including recent announcements, contractor/service rankings, and coverage statistics.120 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables searching New York State government contract awards and aggregating vendor procurement data from the official Procurement Report for State Authorities on data.ny.gov.317 npmMIT