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., "@MEDAS MCP Tüketici fiyat endeksi göstergelerini listele"
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.
MCP server for TÜİK MEDAS (Turkish Statistical Institute indicators).
92 topics — all TÜİK statistical categories
400+ indicators — cached instantly, live fallback available
Dynamic discovery — 0 hardcoded widget IDs, adaptive to UI changes
Cache-first — list_topics/get_indicators/download all <50ms from cache
Binary XLS — xlwt CDFV2 Excel output (same format as MEDAS pivot.xls)
Smart cascading — auto-selects mandatory breakdowns (COICOP, SITC, etc.)
ZK Widget API — robust kırılım handling via zk.Widget.$().fire()
Related MCP server: evds-mcp-server
pip install playwright xlwt httpx
playwright install chromiumOr with uv:
uv pip install -e .
playwright install chromiumpython server.pyAdd to ~/.pi/config.json:
{
"extensions": {
"medas": {
"command": "python",
"args": ["/path/to/medas_mcp/server.py"],
"cwd": "/path/to/medas_mcp"
}
}
}{
"mcpServers": {
"medas": {
"command": "python",
"args": ["/path/to/medas_mcp/server.py"]
}
}
}Tool | Description | Speed |
| List 92 TÜİK topics | <50ms (cache) |
| Get indicators + cascading branches | <50ms (cache) |
| Download XLS/CSV report | <50ms cache / ~12s live |
1. list_topics("fiyat") → [{index:78, label:"Tüketici Fiyat Endeksi"}]
2. get_indicators(78) → {count:12, indicators:[...]}
3. download(78, format="xls") → /tmp/MEDAS_Tüketici_Fiyat_Endeksi_20260820.xlsAI Agent ⇄ MCP (stdio) ⇄ server.py ⇄ medas_client.py
├─ cache (data/*.json) → instant
└─ Playwright (live=true) → ZK AU protocolMode | Source | Speed | Data |
|
| <50ms | Indicator names + mock values |
|
| ~12s | Real MEDAS pivot table |
medas_mcp/
├── server.py # MCP server (3 tools)
├── medas_client.py # Hybrid client (cache + live Playwright)
├── KNOWHOW.md # ZK AU protocol traffic notes
├── AGENTS.md # AI agent instructions
├── README.md # This file
├── pyproject.toml # Package metadata
├── .gitignore
└── data/
├── topic_mapping.json # 92 topics with URLs
├── topic_gosterge.json # Indicators + cascading branches
└── medas_unified.json # Unified datasetPOST /medas/zkau;jsessionid=XXX with dtid + batched cmd_n=onSelect/onClick
Widget IDs change every session — discovered dynamically via DOM
Cascading: zk.Widget.$('#selectId').fire('onSelect', {items:[itemId], reference:itemId})
MIT
This server cannot be deployed
Search and query 1,500+ OECD statistical datasets via SDMX. Keyless.
Macro indicators from World Bank, FRED, IMF, and OECD via unified query surface.
Query 29,500+ World Bank development indicators for 200+ countries across 60+ years.
Discover statistical indicators and topics in Data Commons. Retrieve observations for specific var…