What is luxalgo-mcp-server AGENTS.md?

Repository instructions for coding agents working on the LuxAlgo MCP server. An MCP server is a program that lets AI clients call tools to read data or perform defined operations.

Use them when adding or changing tools in the repository, especially to follow its layout, read the required authentication documentation, avoid direct service calls, and verify changes before finishing.

They give an agent the project’s rules before it changes code, including which files are protected, how application calls must be made, and how authentication errors and tokens must be handled.

How LuxAlgo/luxalgo-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to LuxAlgo/luxalgo-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/LuxAlgo/luxalgo-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/LuxAlgo/luxalgo-mcp-server

Made for: Codex, OpenCode.

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/luxalgo/luxalgo-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/luxalgo/luxalgo-mcp-server/agents-md)

Your own site

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

Per session 1,236 This file is loaded in full into every session.

When invoked 1,236 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.

Model	Per session	Once invoked
Fable 5.1	$0.01236	$0.01236
Opus 5.5	$0.00494	$0.00494
Sonnet 5.5	$0.00247	$0.00247
Haiku 4.5	$0.00124	$0.00124

Measured 27d ago against content hash f77165c11298, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

luxalgo-mcp-server AGENTS.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 27d 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.

AGENTS.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working in this repository (for AI coding agents)

This is @luxalgo/mcp, the LuxAlgo MCP server: tools that AI clients (Claude, ChatGPT, Cursor, …) call to read LuxAlgo data. Most work here is adding or changing tools under src/tools/<domain>/. Read this file, then docs/auth.md in full before touching anything.

Hard rules

Do not modify authentication or infrastructure code — src/auth/, src/platform/app-client.ts, src/server/, src/entries/, api/server.ts, public/oauth/, vercel.json — unless a maintainer explicitly asks for that change in this conversation. If a task seems to require it, stop and say so instead of doing it.
Never check entitlements, plans, roles, or permissions in this repo. The LuxAlgo app decides; this server forwards the user's token and relays the app's answer. docs/auth.md §1 explains why. There is no "is this user Premium" check anywhere here and there must not be one.
Call the app only through appGet() (reads) and appSend() (writes) (src/platform/app-client.ts). Never fetch() app.luxalgo.com directly. Never read, store, log, or print a token. appSend has no anonymous form: it is only for protected tools acting on the signed-in user's own data (today: the journal).
Never catch and swallow AppAuthError / AppPermissionError. Rethrow them from any catch; the auth wrapper turns them into the sign-in / upgrade results the client understands. guarded() in tools/_shared/result.ts already does this.
Never cache a response fetched with a user's token. In-process caches must fetch with appGet(path, query, { access: null }).

Layout

src/tools/<domain>/   one directory per tool domain; index.ts exports a ToolModule
src/tools/_shared/    json/toolError/ok/guarded (result.ts), compact/fmtPct/fmtMoney (format.ts), ToolModule type
src/server/           manifest.ts (list of modules — the only file outside tools/ you edit when adding a domain)
src/auth/             OAuth — read docs/auth.md; do not edit
src/platform/         appGet (the app HTTP client), analytics — do not edit
src/entries/          stdio / node-http / hosted entry points — do not edit
test/                 smoke.mjs runner + smoke/<domain>.mjs, parity.mjs, trackers-check.mjs

Read the full file on GitHub · 49 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.

27d ago Changed · +4 lines · +159 tokens per session f77165c11298
1mo ago Changed · +55 tokens per session 5858ce358225
1mo ago First seen · 45 lines · 1,022 tokens per session scan A e552b995f65d

Subscribe to this mod's changes

luxalgo-mcp-server AGENTS.md is an instructions file published in the GitHub repository LuxAlgo/luxalgo-mcp-server (108 stars, last pushed 12d ago), licensed MIT. It adds 1,236 tokens to every session, about $0.0049 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 2026-09-10.

Building agents Finance and fintech Research Security knowledge-base mcp mcp-server trading

luxalgo-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
luxalgo-mcp-server AGENTS.mdLuxAlgo/luxalgo-mcp-server	Instructions file	108	12d ago	MIT	A	1,236	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

luxalgo-mcp-server: Instructions file for Codex