What is segnals-mcp AGENTS.md?

Written instructions for AI coding agents connected to Segnals, an algorithmic trading platform where users configure automated trading bots for exchanges or forex through MetaTrader 5.

Use them when onboarding users, answering questions about Segnals, or safely handling requests involving trading bots and accounts.

They give agents a consistent explanation of the service, its supported account and bot actions, and its limits, including that funds cannot be moved or withdrawn.

How eidostein/segnals-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to eidostein/segnals-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/eidostein/segnals-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/eidostein/segnals-mcp

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

Your own site

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

Per session 3,888 This file is loaded in full into every session.

When invoked 3,888 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	$0.03888	$0.03888
Opus 5.5	$0.01555	$0.01555
Sonnet 5.5	$0.00778	$0.00778
Haiku 4.5	$0.00389	$0.00389

Measured 28d ago against content hash 743f2eb7541d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

segnals-mcp 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 28d 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 · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Segnals MCP — Agent Playbook

This file is for AI agents (Claude, Cursor, Copilot, Windsurf, etc.) that connect to the Segnals MCP server. Follow this playbook to onboard users, answer questions, and manage their trading bots safely.

1. How to Explain Segnals

When a user asks what Segnals is, use this:

Segnals is an institutional-grade algorithmic trading platform. You configure trading bots that run 24/7 on exchanges like Bybit and Phemex, or MetaTrader 5 for forex. This MCP server lets me interact with your account — I can read your stats, manage your bots, copy marketplace strategies, and configure your trading setup.

What this MCP CAN do

✅ Read account details, PnL, performance, trade history
✅ Create, configure, start, stop, restart, and delete trading bots
✅ Create full strategies (bot + config in one call)
✅ Copy strategies from the marketplace (free or paid)
✅ Publish your strategies to the marketplace
✅ Configure indicator filters (ADX, RSI, EMA, ATR)
✅ Control copy trading (start/stop per exchange)
✅ Manage notification preferences

What this MCP CANNOT do

❌ Move, withdraw, or transfer funds
❌ Access exchange API keys, secrets, or MT5 passwords
❌ Perform admin actions or change email/password
❌ Execute shell commands or visit URLs
❌ Process affiliate payouts

For full details, see SAFETY.md.

2. Onboarding Script

When a user wants to get started, walk them through this exact flow:

Step 1: Create an Account

You'll need a Segnals account. Go to segnals.com and sign up if you haven't already.

Step 2: Generate an API Key

Go to Settings → API Keys and click Create New Key. Give it a name like "Claude MCP" or "My AI Agent".

Step 3: Select Scopes

Choose which permissions to grant. I recommend starting with read-only to explore:

Scope	What it unlocks
`read:account`	Account details, subscription, connections
`read:stats`	Dashboard, PnL, performance, trades
`read:bots`	Bot list, config, logs, strategy schema
`write:bots`	Create, update, delete bots
`control:bots`	Start, stop, restart bots
`write:strategies`	Create strategies with full config
`read:marketplace`	Browse marketplace listings
`write:marketplace`	Copy and publish strategies
`read:news`	Market newsfeed
`manage:notifications`	Notification preferences

Read the full file on GitHub · 339 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.

28d ago Changed · +17 lines · +413 tokens per session 743f2eb7541d
2mo ago First seen · 322 lines · 3,475 tokens per session scan A 6f02d002f730

Subscribe to this mod's changes

segnals-mcp AGENTS.md is an instructions file published in the GitHub repository eidostein/segnals-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 3,888 tokens to every session, about $0.0156 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.

Finance and fintech

segnals-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
segnals-mcp AGENTS.mdeidostein/segnals-mcp	Instructions file	0	28d ago	MIT	A	3,888	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

segnals-mcp: Instructions file for Codex