tossinvest-openapi-mcp: Instructions file for Claude Code

CLAUDE.md

tossinvest-openapi-mcp CLAUDE.md is an instructions file for Claude Code from JeongSeongMok/tossinvest-openapi-mcp. It costs 612 tokens per session, scanned A, original, MIT.

A project instruction file for AI coding assistants working with a read-only MCP server for the Toss Securities Open API. MCP is a standard way for assistants to use tools; this server explains the API from a bundled specification but never contacts Toss or handles credentials.

In plain words
What is it for?
Use it to find API operations and data schemas, read integration guides, or generate curl, TypeScript, and Python request examples.
Why use it?
It tells the assistant how the API description is stored, searched, formatted, and turned into example requests without making real financial API calls.

Instructions file for Claude Code

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

This is JeongSeongMok/tossinvest-openapi-mcp's own configuration. It tells Claude Code how to work on tossinvest-openapi-mcp 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 tossinvest-openapi-mcp configures →

Reuse

Borrowing it

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

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 tossinvest-openapi-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jeongseongmok/tossinvest-openapi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jeongseongmok/tossinvest-openapi-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 612 This file is loaded in full into every session.
When invoked 612 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 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 $0.00612 $0.00612
Opus 5 $0.00306 $0.00306
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 11d ago against content hash 70c1ad581604, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tossinvest-openapi-mcp 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 11d 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.

- `src/codegen.ts` — generates curl / TypeScript / Python request samples.
CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for AI agents (Claude Code and others) working in this repository.

What this is

An MCP (Model Context Protocol) server, distributed via npm and run over stdio, that exposes the Toss Securities (토스증권) Open API specification as agent-friendly tools.

It is read-only: it explains the API, it never calls it. There is no authentication, no network access at runtime, and no account/credential handling. All data comes from the bundled openapi.json.

Architecture

  • openapi.json — the bundled Toss Securities OpenAPI 3.1 document. Source of truth.
  • src/spec/store.ts — loads openapi.json once, flattens operations, indexes tags & schemas, and resolves local $refs (with cycle protection via deref).
  • src/format.ts — renders operations and schemas as compact, agent-readable markdown.
  • src/codegen.ts — generates curl / TypeScript / Python request samples.
  • src/guides.ts — curated, use-case-oriented integration guides; each step references a real operationId that is validated against the spec at request time.
  • src/server.ts — registers all MCP tools (McpServer.registerTool) with zod input schemas.
  • src/index.ts — stdio entry point (#!/usr/bin/env node).

Conventions

  • Tool descriptions are written for agents, in English — imperative, action-oriented, and they cross-reference related tools (e.g. "use get_endpoint for full detail").
  • Tool output is markdown text, optimized for token efficiency: lists/overviews first, full detail via a drill-down tool. Never dump raw JSON when a field tree is clearer.
  • Never invent spec content. If something is not in openapi.json, say so.
  • stdio servers must not write to stdout; all logging goes to stderr.

Build & verify

npm install
npm run build          # tsc → dist/
node dist/index.js     # starts the stdio server (logs to stderr)

To smoke-test tools, drive the server with MCP JSON-RPC over stdio (initializenotifications/initializedtools/listtools/call).

Read the full file on GitHub · 56 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. 11d ago First seen · 56 lines · 612 tokens per session scan A 70c1ad581604

Subscribe to this mod's changes

tossinvest-openapi-mcp CLAUDE.md is an instructions file published in the GitHub repository JeongSeongMok/tossinvest-openapi-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories