MCP server exposing 3 tools for prozorro.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/prozorro/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}prozorro_recent_tenders — Most recently updated tenders from Ukraine's ProZorro national procurement system (via the keyless OpenProcurement public feed). Returns each tender with id, tenderID, title, value (amount+currency, usually UAH), buyer (procuring entity), status, and procurement method. Titles and buyer names are in Ukrainian. Use for browsing current Ukrainian public tenders; for a specific tender use prozorro_get_tender.prozorro_search_tenders — Keyword search over recent Ukraine ProZorro tenders (keyless OpenProcurement public feed). Best-effort: scans the recent public feed and returns tenders whose title/buyer/tenderID match the query (case-insensitive substring; Ukrainian text supported — pass Ukrainian keywords for best recall). Returns id, tenderID, title, value, buyer, status. NOTE: this is not a full-text index of all history — ProZorro's front-end search API is not reachable from datacenter egress, so this filters the recent feed only. For older or exact tenders use prozorro_get_tender with a known id.prozorro_get_tender — Full detail for a single Ukraine ProZorro tender by id (via the keyless OpenProcurement public API). Returns tenderID, title, description, status, procurement method, value (amount+currency), the buyer/procuring entity (name, EDR identifier, region, contact), tender period (start/end), enquiry period, number of bids, and line items (description, CPV classification, quantity, unit). Text is largely Ukrainian. Accepts the 32-char tender id from prozorro_recent_tenders / prozorro_search_tenders.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/prozorro/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io