In-depth architectural comparison of the MCP Server and Kagimcp MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
MCP Server
Search & Data Extraction · Local stdio
Quality: 56/100 (Good) | Auth: API Key required
Kagimcp
Search & Data Extraction · Local stdio
Quality: 80/100 (Excellent) | Auth: API Key required
Verdict Summary: Choose MCP Server if you need specialized Search & Data Extraction tools running via a local process. Choose Kagimcp if your workspace requires Search & Data Extraction integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose MCP Server when:
You need dedicated capabilities in the Search & Data Extraction domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Free / Open Source).
You have access to required keys: ATLAS_API_BASE, ATLAS_API_KEY, ATLAS_TIMEOUT_MS, ATLAS_MAX_RETRIES.
Search 800 000+ Polish public tenders (BZP + TED). Profiles of procuring entities and contractors by NIP, market statistics by CPV/province, 90+ term procurement glossary.
The Official Model Context Protocol (MCP) server for Kagi Search & other tools.
Category & Scope
Tools & Capabilities Breakdown
MCP Server Tools (8)
search_tenders
Search public procurement tenders from BZP (Biuletyn Zamówień Publicznych) and TED (Tenders Electronic Daily) via Atlas Przetargów. Returns a list with titles, buyers, locations, CPV codes, estimated values and deadlines. Use for queries like 'aktywne przetargi budowlane w Warszawie', 'zamówienia IT powyżej 500k PLN', 'co kupuje ZUS'.
get_tender
Retrieve detailed information about a specific Polish public tender by its ID. Returns buyer, location, deadlines, estimated value, CPV codes, contractor (if awarded), notice type and a content excerpt. Optionally includes AI-generated summary points (requires ATLAS_API_KEY).
get_buyer
Fetch a profile of a Polish public procuring entity (zamawiający) by its NIP (tax ID). Returns name, location, statistics, recent tenders, and top winning contractors. Use for due diligence on who buys what and from whom.
get_contractor
Fetch a profile of a Polish tender contractor by its NIP. Returns name, location, total wins, total value and top buyers they win tenders from.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
MCP Server is categorized under Search & Data Extraction and uses a local stdio subprocess. In contrast, Kagimcp belongs to Search & Data Extraction using local stdio subprocess. Select MCP Server when you need capabilities focused on search & data extraction and Kagimcp when you require tools for search & data extraction.
Search Polish public procurement entities (buyers / zamawiający) or contractors (wykonawcy) by name. Returns a list with NIP, location and volume. Useful to find the NIP for get_buyer / get_contractor tools.
get_category_stats
Retrieve aggregate statistics for a CPV category: count, average/median value, average number of offers, average deadline period. Based on historical BZP+TED data. Useful for market sizing and competitive benchmarking.
get_province_stats
Retrieve aggregate tender statistics by Polish province (all 16 voivodeships) or drill down to a specific city (top buyers, top CPV categories). Without arguments returns the full province ranking.
search_cpv
Look up CPV (Common Procurement Vocabulary — EU procurement category) codes by Polish keyword. Use this before search_tenders to find the right CPV filter. Returns code, name, division, and historical tender count.
Kagimcp Tools (2)
kagi_search_fetch
Fetch web results for a query using the Kagi Search API. Use for general search and when the user explicitly tells you to 'fetch' results/information. Results are numbered so that a user may refer to a result by a specific number.
kagi_extract
Extract the content of a web page as markdown using the Kagi Extract API. Use this to read the full content of a page when needed.