What is kite-mcp-server CLAUDE.md?

Project instructions for the Kite MCP Server, which connects an AI assistant to a Zerodha Kite trading account through MCP, a standard way to provide tools to AI clients.

Use them when developing, deploying, or operating the Kite MCP Server and its trading, paper-trading, research, or alert features.

They help a new Claude session understand the repository, its commands, deployment options, and the difference between read-only hosted use and self-hosted trading.

How Sundeepg98/kite-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Sundeepg98/kite-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Sundeepg98/kite-mcp-server/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Sundeepg98/kite-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sundeepg98/kite-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/sundeepg98/kite-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sundeepg98/kite-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sundeepg98/kite-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sundeepg98/kite-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sundeepg98/kite-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,315 This file is loaded in full into every session.

When invoked 2,315 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin fork From a forked repository.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.02315	$0.02315
Opus 5	$0.01157	$0.01157
Sonnet 5	$0.00463	$0.00463
Haiku 4.5	$0.00231	$0.00231

Measured 8d ago against content hash a8bb3ec0c20b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kite-mcp-server CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8080/healthz # health probe ("ok")

CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Kite MCP Server

Orientation for a fresh Claude session. Keep this a stable map; volatile status lives in README.md / git / the docs below, not here.

What it is

Kite MCP Server (github.com/Sundeepg98/kite-mcp-server, Go 1.25, MIT) - an MCP server that gives Claude / ChatGPT / any MCP client direct access to a Zerodha Kite trading account: order placement, paper trading, options Greeks, backtesting, Telegram alerts, and RiskGuard (11 pre-trade safety checks). 110+ tools. Complementary to Zerodha's official read-only MCP (which is 22 tools, GTT only).

Two ways it runs, and the distinction matters for everything below:

Mode	Where	Trading	Notes
Hosted demo	Fly app `kite-mcp-server` (region `bom`), `https://kite-mcp-server.fly.dev/mcp`	READ-ONLY	`ENABLE_TRADING=false` gates off all 18 order-placement tools. This is a legal posture, not a feature gap (see SEBI note).
Self-host	`Dockerfile.selfhost` / `docker compose up -d`, `http://localhost:8080/mcp`	FULL	Personal-use safe harbor - you remain the Zerodha Client; the software just helps you place your own orders. Set `OAUTH_JWT_SECRET`.

Branch / repo

Active branch is master (not main/development). Remote Sundeepg98/kite-mcp-server.
Deploy is MANUAL. git push origin master does NOT auto-deploy (contrast appscriptly, which auto-deploys on push). CI (.github/workflows/ci.yml) runs go build / go vet / go test -race; smoke-canary.yml smoke-tests the live URL every 30 min. To ship a change you must run flyctl deploy -a kite-mcp-server yourself.

Commands

go build -o kite-mcp-server && ./kite-mcp-server   # local build/run (Go, no Docker)
docker compose up -d                               # self-host full-trading (Dockerfile.selfhost)
go test ./... -count=1                              # tests (run per module; ~9000 across 32 algo2go modules + deploy repo)
curl http://localhost:8080/healthz                 # health probe ("ok")

# Deploy the hosted app (MANUAL):
flyctl deploy -a kite-mcp-server                                   # full build + deploy from Dockerfile
flyctl deploy -a kite-mcp-server --image <current-image> --config fly.toml -y   # config-only, no rebuild (safest for a trading app)
flyctl status -a kite-mcp-server                                   # machine state / version / live image
flyctl logs -a kite-mcp-server --no-tail                          # boot + runtime logs

Read the full file on GitHub · 63 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 63 lines · 2,315 tokens per session scan A a8bb3ec0c20b

Subscribe to this mod's changes

kite-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Sundeepg98/kite-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 2,315 tokens to every session, about $0.0116 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It comes from a forked repository.

Finance and fintech ai-trading algorithmic-trading backtesting chatgpt claude fintech

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

kite-mcp-server: Instructions file for Claude Code