atlas-przetargow-mcp-py
Enables searching and analyzing Polish public procurement tenders from BZP and TED, including filtering, tender details and timelines, offers and contract values, buyer/contractor profiles, CPV code lookup, and regional statistics, with optional AI-summary endpoints.
README
atlas-przetargow-mcp-py
Atlas Przetargow Polish public procurement API MCP server. A Python/FastMCP rewrite of the official TypeScript server with several upstream bugs fixed and new tender-analysis tools added.
Table of contents
Tools
| Tool | Parameters | Description |
|---|---|---|
search_tenders |
search?, buyer_nip?, cpv?, city?, province?, notice_type?, order_kind?, date_from?, date_to?, value_min?, value_max?, sort?, page=1, limit=20 |
Search BZP + TED tenders with filters |
get_tender |
tender_id: str, full: bool = False |
Tender details; full=True includes complete notice text |
get_tender_timeline |
tender_id: str |
Full notice chain of a procedure (announcement, revisions, result, performance) |
get_tender_offers |
tender_id: str |
Offers count and lowest/highest/winning prices from result notices |
extract_contract_value |
tender_id: str |
Contract/order money amounts extracted from notice text |
get_buyer |
nip: str, include_winning_contractors: bool = True |
Buyer profile + contractors that most often win its tenders |
get_contractor |
nip: str, include_winning_buyers: bool = True |
Contractor profile with win geography + top buyers |
search_entities |
query: str, entity_type?, limit=10 |
Find buyers/contractors by name (returns NIP) |
search_cpv |
query: str, limit=10 |
Look up CPV codes by Polish keyword |
get_category_stats |
cpv: str, window="year" |
Category stats: count, median value, avg offers, avg deadline |
get_province_stats |
province?, city? |
Province ranking, single province, or city drill-down |
raw_request |
path: str, params_json? |
Escape hatch: GET any /api/* endpoint |
Fixed vs upstream TS server
Bugs found while testing @atlasprzetargow/mcp v0.1.1:
buyerNipfilter sent asbuyerNipwhile the API expectsbuyer_nip— filter silently ignored. Fixed here.get_buyerwinning contractors read fromwinners.contractorswhile the API returns{"data": [...]}— section never rendered. Fixed here.- City stats returned an empty header although
/api/stats/city/{city}/top-buyersreturns data. Fixed here. get_category_statsrequested window can be ignored by the API (asks for year, returns 90 days) — this server returns the actualdaysvalue so the discrepancy is visible.get_contractorreturned 3 lines; this server returns the full profile (win geography, shares) plus winning buyers.
New tools not present upstream: get_tender_timeline, get_tender_offers, extract_contract_value, raw_request.
Environment variables
| Variable | Required | Description |
|---|---|---|
ATLAS_PRZETARGOW_MCP_PY_API_BASE |
no | API base (default https://atlasprzetargow.pl) |
ATLAS_PRZETARGOW_MCP_PY_API_KEY |
no | Key for /api/llm/* AI summary endpoints |
ATLAS_PRZETARGOW_MCP_PY_TIMEOUT |
no | Request timeout in seconds (default 20) |
Wiring it up
Only requirement: uv (https://docs.astral.sh/uv/). Nothing else to install.
Claude Code
claude mcp add atlas-przetargow-mcp-py -- uvx --from git+https://github.com/dam2452/atlas-przetargow-mcp-py.git atlas-przetargow-mcp-py
Claude Desktop / other MCP client
{
"mcpServers": {
"atlas-przetargow-mcp-py": {
"command": "uvx",
"args": ["--from", "git+https://github.com/dam2452/atlas-przetargow-mcp-py.git", "atlas-przetargow-mcp-py"]
}
}
}
After pushing a new version: uv cache clean and restart the client.
Local run
uv run --directory . atlas-przetargow-mcp-py
Tests (manual):
uv run --directory . --with pytest pytest test/
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。