trading-mcp-server: Instructions file for Claude Code

CLAUDE.md

trading-mcp-server CLAUDE.md is an instructions file for Claude Code from mukul8896/trading-mcp-server. It costs 1,055 tokens per session, scanned A, original, MIT.

A set of project instructions for building trading-mcp-server, a Python package that provides guarded tools for Indian stock-market data, simulation, and broker actions. It defines where code belongs and which modules may access the real broker.

In plain words
What is it for?
Use it when adding or modifying services, MCP tools, broker integration, configuration, storage, or server wiring in the trading-mcp-server repository.
Why use it?
It gives coding agents clear boundaries for changing the package without breaking its structure or weakening the safety layer around real orders. It also prevents the package from depending on a separate trading workspace.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is mukul8896/trading-mcp-server's own configuration. It tells Claude Code how to work on trading-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything trading-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mukul8896/trading-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/mukul8896/trading-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mukul8896/trading-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.

agentmods badge for trading-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mukul8896/trading-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/mukul8896/trading-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mukul8896/trading-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/mukul8896/trading-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.

agentmods 80×15 button for trading-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mukul8896/trading-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/mukul8896/trading-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,055 This file is loaded in full into every session.
When invoked 1,055 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01055 $0.01055
Opus 5.5 $0.00422 $0.00422
Sonnet 5.5 $0.00211 $0.00211
Haiku 4.5 $0.00105 $0.00105

Measured 2mo ago against content hash 24793f0a144f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trading-mcp-server CLAUDE.md scanned grade A with 0 findings 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — trading-mcp-server

Project context

This repo is a standalone, pip-installable Python package that implements a local MCP with safe trading tools (NSE / Angel One). It is consumed by trading workspaces (e.g. the sibling TradingAgent repo) but must never depend on them. The agent using the tools lives elsewhere — this package only provides data, validation, simulation, and a guarded broker layer.

Package structure rules

  • src/ layout, import package trading_mcp_server, distribution name trading-mcp-server. Do not break this naming or move out of src/.
  • server.py only wires things together (create_server()); logic lives in services/, tool registration in tools/ (one module per category, each exposing register(mcp)), MCP resources/prompts in their packages.
  • broker/smartapi_adapter.py is the ONLY module that talks to the real broker, and services/broker_service.py is the ONLY caller of its order methods. Keep it that way — that's what makes the safety layer auditable.
  • All filesystem state goes under get_storage_dir(); all config through config.get_config(). Both resolve from TRADING_MCP_HOME (or cwd). Never hardcode a repo path, user path, or absolute path.
  • Heavy/optional imports (SmartApi, bs4) stay lazy so paper-mode users and tests run without the [broker,scanners] extras.

MCP tool design rules

  • Tools return plain JSON-serializable dicts; errors as {"error": ...} via tools/_common.make_tool — never let raw tracebacks reach the agent.
  • Docstrings are the agent-facing contract: state what the tool does, its enums (e.g. timeframes), and any safety behavior.
  • All order placement goes through the single place_order tool → broker_service.place_order, which calls validate_order and routes by EXECUTION_MODE. Never add a tool that places orders by another path.
  • Tools must never return secrets; config goes out via to_safe_dict() only.
  • Logs go to stderr (utils/logger.py); stdout belongs to the MCP transport.

Read the full file on GitHub · 86 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.

  1. 2mo ago First seen · 86 lines · 1,055 tokens per session scan A 24793f0a144f

Subscribe to this mod's changes

trading-mcp-server CLAUDE.md is an instructions file published in the GitHub repository mukul8896/trading-mcp-server (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,055 tokens to every session, about $0.0042 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

trading-mcp-server CLAUDE.md compared with instructions from other repositories

trading-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
trading-mcp-server CLAUDE.mdmukul8896/trading-mcp-serverInstructions file04mo agoMITA1,055Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot