Skip to content
Agentmart
Submit a tool

Prozorro

Ukrainian public procurement (Prozorro): open tenders, plans, competitors, red flags.

Connector by kotiniiqq · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1
Write a review

Chalk Labs

Need help deploying Prozorro?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/kotiniiqq-prozorro-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Ukrainian public procurement (Prozorro): open tenders, plans, competitors, red flags. No keys.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.

Tools
5 read · 1 write · 0 delete · 8 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Tools by what they do 14

Read from the source code; the running server may list different tools.

Read 5 · Look things up without changing anything.

  • find_entity
  • get_tender
  • search_tenders
  • upcoming_plans
  • watch_digest

Write 1 · Create, change, send or run things.

  • sync_data

Not yet classified 8 · We could not tell from the name and description.

  • buyer_profile
  • competitors
  • coverage
  • market_overview
  • red_flags
  • supplier_profile
  • watch_add
  • watch_remove

Network hosts it talks to 4

  • github.com · found in code
  • glama.ai · found in code
  • prozorro.gov.ua · found in code
  • public-api.prozorro.gov.ua · found in code

Files it touches

  • Your home directory (~)

Tools (14)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • buyer_profile

    Buyer profile by EDRPOU: what it buys, from whom, procedure mix, share of competitive tenders with a single bidder.

  • competitors

    Who competes with a company (EDRPOU): bidders met most often in the same tenders, and how many of those tenders each side won.

  • coverage

    What the local data covers: regions, period, CPV filter, counts, last sync, the background sync progress if any, and how to add more. Call this first when unsure.

  • find_entity

    Find buyers and suppliers by part of a name (or an exact EDRPOU code). role: any, buyer, supplier.

  • get_tender

    One tender in full by its UA-... id: items with quantities and CPV, lots, every bid, the winner, and documents with direct links.

  • market_overview

    Market for a CPV and/or region over a period: number and value of tenders, awarded sum, share of competitive procedures, average bidders, unit-price spread (P25/median/P75, same CPV and unit), top buyers and winners.

  • red_flags

    Red flags for a buyer (EDRPOU), CPV or region, each with evidence and a link: single_bidder, supplier_concentration (one supplier > share of a buyer's spend), price_above_median (unit price pct above peers), short_tender_period. A flag is a reason to look closer, not proof.

  • search_tenders

    Search tenders. Words match the title and item descriptions; cpv is a ДК 021 code, prefix or words; region in any spelling; status: open (default, accepting bids), any, or a Prozorro status. Dates as 2026-10-01, 7d or 24h. Returns tender ids, buyers, amounts, deadlines and links.

  • supplier_profile

    Supplier profile by EDRPOU: wins and their value, main buyers and CPVs, win rate where it bid, median discount from the expected value. Use find_entity to get the code from a name.

  • sync_data

    Download Prozorro tenders and plans for regions (any spelling) into the local data, in the background. Call it only after the user agreed to the download. days: how far back; the user chooses it for the first download, later downloads keep the synced period unless the user asks for another. cpv: categories to download, added to those already synced (nothing changes when all categories are synced). Without arguments it fetches what changed since the last sync. Regions are added to what is already synced; a new region, category or period walks the whole period again. Returns at once; check cover…

  • upcoming_plans

    Upcoming purchases from annual plans that have no tender yet: see demand before it is announced. Filter by words, CPV, region, budget, planned start date.

  • watch_add

    Save a search under a name (words, CPV code or words, region in any spelling) so watch_digest shows its new tenders. Call it when the user asks to follow something.

  • watch_digest

    New tenders for the user's saved searches since a moment (default: last 24 hours). Saved searches are added with watch_add or the CLI: prozorro-mcp watch add.

  • watch_remove

    Delete a saved search by its name. Only when the user asks to stop following it.

Signals

Stars
1
Forks
0
Open issues
0
Weekly downloads
43
Last commit
Oct 22, 2026 (9 days ago)
Last release
Oct 13, 2026 (18 days ago)
Last package publish
Oct 13, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.kotiniiqq/prozorro-mcp
Version
0.1.1
Auth
No auth
Packages
pypi prozorro-mcp
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from kotiniiqq

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get Prozorro running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying Prozorro?

CallGet help
Cite this page

Prozorro MCP server. Agent Mart. https://agentmart.dev/connectors/kotiniiqq-prozorro-mcp (last updated 2026-10-24)