MCP servers are just REST APIs in a polite wrapper - here's 5 lines of Python

A developer demonstrated that MCP (Model Context Protocol) servers are essentially REST APIs with a polite wrapper, showing how to access the Helium MCP server's underlying HTTP endpoints directly using Python's `requests.get()` in just five lines of code. The Helium MCP server, which provides ML option fair values and 31-dimension news-bias scores, offers 50 free queries per IP without requiring signup or an API key, making it accessible for integration into Streamlit apps, Jupyter notebooks, or Discord bots without ever using Claude Desktop.

If you've been watching the MCP Model Context Protocol ecosystem from the sidelines, here's a quietly important detail: a lot of MCP servers are also just plain REST APIs underneath. The MCP layer is a polite wrapper that says "Claude, here are tools you can call." But the underlying HTTP endpoints are right there, ready to be called from requests.get ... like any other JSON API. That matters because the most interesting MCP servers are useful even if you've never opened Claude Desktop or Cursor. You can drop them into a Streamlit app, a Jupyter notebook, a Lambda function, a Discord bot, an Airflow DAG, or a cron job. The MCP integration is gravy on top. I'll show this with a concrete example: pulling per-symbol ML option fair values and 31-dimension news-bias scores into pandas in 5 lines. I run Helium MCP https://github.com/connerlambden/helium-mcp , which started as an MCP server and recently grew a plain REST surface. Both speak the same data: The MCP endpoint is https://heliumtrades.com/mcp . The REST endpoints live under https://heliumtrades.com/ with paths like /mcp search/ , /mcp option price/ , /mcp ticker/ , /mcp url bias/ . 50 free queries per IP. No signup, no API key needed for the free tier. python import requests r = requests.get "https://heliumtrades.com/mcp search/", params={"q": "apple earnings", "limit": 3}, timeout=30, print r.json You get back a JSON list of articles with full bias scoring across all 31 dimensions per article: credibility , sensationalism , overconfidence , opinion vs fact , scapegoating , ai authorship probability , covering responses , oversimplification , and 23 more. This is where it gets fun. The JSON is already flat enough that pandas just works: python import pandas as pd, requests resp = requests.get "https://heliumtrades.com/mcp search/", params={"q": "federal reserve", "limit": 50}, df = pd.json normalize resp.json print df "source", "credibility", "sensationalism", "opinion vs fact" .head Now you can do everything pandas does: groupby source, compute mean credibility, plot a credibility-vs-sensationalism scatter, filter to high-AI-authorship-probability articles, etc. python import requests r = requests.get "https://heliumtrades.com/mcp option price/", params={ "symbol": "AAPL", "strike": 200, "expiration": "2026-06-19", "option type": "call", }, print r.json {'predicted price': 20.64, 'prob itm': 0.52, 'delta': 0.55, 'gamma': 0.02, 'vega': 0.41, ...} You get back a model-derived fair value and prob ITM next to market price. The diff between the two is a testable, scorable prediction. Once the API returns JSON, building a Streamlit app is essentially a wrapper exercise: python import streamlit as st, requests, pandas as pd q = st.text input "Search query", "tariffs" limit = st.slider "Results", 1, 50, 10 if st.button "Go" : resp = requests.get "https://heliumtrades.com/mcp search/", params={"q": q, "limit": limit}, df = pd.json normalize resp.json st.dataframe df "title", "source", "credibility", "sensationalism", "ai authorship probability" st.bar chart df.groupby "source" "credibility" .mean This is the smallest realistic media-bias dashboard I've ever written. It's about 12 lines. The point isn't that this one API is special. The point is that MCP servers with REST surfaces are a quietly powerful new class of API. They are: If you're a data scientist who's never installed Claude Desktop and never wants to: that's fine. Treat MCP servers as a directory of unusually well-curated free REST APIs and start with the ones that solve a problem you already have. For finance and news intelligence specifically, the full Helium MCP REST endpoint list is: | Endpoint | Purpose | Params | |---|---|---| /mcp search/ | News search across 3.2M articles | q , limit | /mcp balanced search/ | Multi-perspective news synthesis | q , limit | /mcp source bias/ | 31-dim bias profile for one source | source | /mcp url bias/ | 31-dim bias profile for one article URL | url | /mcp all source biases/ | All scored sources | - | /mcp ticker/ | Real-time market data for a symbol | ticker | /mcp option price/ | ML option fair value + Greeks | symbol , strike , expiration , option type | /mcp historical options/ | Full options chain with ML fair values | symbol , date | /mcp top strategies/ | AI-ranked options strategies | limit , sort | /mcp meme search/ | Semantic meme search | q , limit | The MCP server config for Cursor / Claude Desktop / Windsurf is: { "mcpServers": { "helium": { "url": "https://heliumtrades.com/mcp" } } } But honestly - if Python is your thing - just open a notebook and requests.get . The whole point of a public REST surface is that you don't have to care about anything else. Source, schema, full tool spec: github.com/connerlambden/helium-mcp https://github.com/connerlambden/helium-mcp . Page: heliumtrades.com/mcp-page https://heliumtrades.com/mcp-page/ . If you build something with it, I'd love to see it. Open an issue, or send a notebook - happy to feature good demos.