Sancho Fetch MCP server

Sancho Fetch

<!-- mcp-name: io.github.panth-net/sancho-fetch -->

Ask your AI for public data. Get real files on your computer.

The fastest way in: tell your AI

Open your AI's code mode -- Claude desktop app -> Code tab, or ChatGPT desktop app -> Codex -- pick any folder, and paste this:

Install Sancho Fetch from PyPI (uv tool install sancho-fetch) and set it

up on this computer. If uv isn't installed, tell me, then install it

first. When you're done, tell me whether the install succeeded. Then

explain in plain English, no jargon: what the .env file is, how to use it,

where it is on my computer, and open it for me so I can paste API keys

straight into it. Give me a few examples of data sources that need a free

API key and a few examples of sources that don't need a key. Tell me where

my downloaded data gets saved, and how I update Sancho later. Then run a

short example data fetch using the World Bank so I can see where the data

was saved. Finally tell me a few natural language examples I can tell you

to fetch data so I can get a feel for how to use sancho-fetch and remind

me that 1) I can use it anywhere as long as I'm in a LLM Desktop app's

Code tab (e.g. ChatGPT Desktop or Claude Desktop), and 2) that I can ask

AI to add new data sources by itself since sancho-fetch is built in a way

that it's easily extensible (aka you can add more to it and the AI will do

the heavy lifting and connect the new data source).

That's the whole install.

You do not need to download or clone this repository. The two commands the AI runs are:

uv tool install sancho-fetch
sancho setup

Install once, use everywhere. Sancho installs once on your computer and connects to the AI apps it finds (Claude Desktop, ChatGPT/Codex, VS Code, Cursor). At the end of setup it tells you plainly which apps are ready and which just need a restart or a click.

To use Sancho, just ask for data and mention "sancho" in plain English, or type /sancho in Claude Code to feel cool.

What it does

You can be working in any folder -- Sancho always knows where its home folder is.

• In your AI's Code mode you ask: "get county-level asthma rates for Ohio."

FDA, USGS, FEMA, ...) and hands you a file that opens in Excel.

• Your AI uses Sancho to pull from 120+ public sources (Census, World Bank,

• Everything is saved on your computer.

Before you begin

The normal prerequisite is uv. uv installs Sancho in isolation and can obtain a compatible Python without replacing your computer's system Python. First setup needs an internet connection. API keys are not required for installation or the World Bank example; provider-specific keys can be added later.

Get started (about 2 minutes)

Install straight from PyPI.

1. Open your AI's code mode.

• Claude: Claude desktop app -> Code tab -> new session -> pick any folder where you want your data to live.
• ChatGPT: ChatGPT desktop app -> Codex -> open that folder.

2. Paste the install request from the top of this page.

The AI installs everything, shows you your first data file, and walks you through where everything lives.

3. Restart the apps Sancho asks you to restart. Setup ends with a short report; if an app needs a restart or one extra click, it says so in plain words.

NOTE: Before using, make sure to add API keys for any sources you want to use.

Many sources need no key (World Bank, USGS, FEMA, openFDA, ...). Your AI will tell you when an API key is needed. You can either:

into the chat**.

1. Open the .env file in the sancho-workspace folder and paste your key there; or
2. Ask your AI to open the keys file for you (sancho env open). Paste the key into the opened file, **don't paste your key

Shortened. The full README is on GitHub.