Screen NSE stocks with Claude over MCP

You can hand an AI agent the entire NSE cash market as a set of tools. PatternsRadar exposes a Model Context Protocol server, and once it is connected, "find NSE stocks above their 200-day average where delivery has stayed over 55% all week" is not a feature request — it is a prompt, answered against that evening's data.

This works on every plan, including Free. An API key authenticates both the REST API and MCP, and creating one takes a minute in your account settings.

The one-line setup

For Claude Code:

claude mcp add --transport http patternsradar https://api.patternsradar.com/mcp --header "Authorization: Bearer prdr_YOUR_KEY"

Any other MCP client that speaks streamable HTTP takes the same URL and header — the MCP docs page has the JSON config and a TypeScript SDK example.

Why the agent doesn't need a manual

The usual failure mode of "LLM + market data API" is the model guessing at a query syntax it has never seen. The PatternsRadar server sidesteps this with a tool called sift_reference: it returns the complete, machine-readable reference for the Sift query language — every field, indicator, operator and pattern — generated from the same catalog the compiler itself reads. An agent calls it once, then writes valid scans for the rest of the session.

That matters because Sift is the interesting part. The language has event operators most screeners cannot express:

delivery_pct has been above 55 for 5 bars

is the whole of the sustained delivery scan. An agent that can write these can compose setups you would not bother clicking together.

A real session

A workflow that takes about two minutes of conversation:

1. Ask for candidates. "Run a scan for NSE stocks above the 200-day average with delivery over 1.5× their 20-day norm." The agent calls run_scan; the shape it gets back is deliberately narrow — symbol, close, change, volume, RSI, delivery — so it does not drown its own context.
2. Make it prove the setup. "Before I look at these — has that scan actually worked?" The agent calls hitrate, which replays the query across the last 250 sessions and reports what matches did over the next 1, 5 and 20 days.
3. Keep what survives. "Save it as 'quiet strength' and I'll watch it." The save_scan tool writes it to your account, where end-of-day alerts can pick it up.

The honest caveat, which the server's own tool descriptions state: the hit rate is a sketch, not a backtest — close-to-close returns, no costs, no slippage. It answers "has this setup been worth a look?", not "what would I have earned?"

What this is actually for

Screens like delivery surge and quiet accumulation exist as pages because they are common questions. The MCP server is for the questions that are yours alone — the setup you half-believe in and want tested, the nightly research note you want assembled by a script that reads like a colleague. The data is end-of-day only and NSE only; within that boundary, an agent with these ten tools is a competent research assistant with thirty years of memory.

The full tool list, parameter shapes and limits are on the MCP page; the same capabilities over plain HTTP live in the API reference.