What is algochains-mcp-server AGENTS.md?

A set of instructions that explains how the AlgoChains MCP server works, including its identity, connection method, operating modes, safety levels, and tool groups.

Read it before using AlgoChains tools, especially when setting up access, choosing paper or live trading, or deciding which safety tier applies.

It gives an AI agent the context needed to choose the right tools and follow the server’s safety rules instead of guessing.

How AlgoChains/algochains-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to AlgoChains/algochains-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/AlgoChains/algochains-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/AlgoChains/algochains-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/algochains/algochains-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/algochains/algochains-mcp-server/agents-md)

Your own site

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

Per session 9,231 This file is loaded in full into every session.

When invoked 9,231 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	$0.09231	$0.09231
Opus 5.5	$0.03692	$0.03692
Sonnet 5.5	$0.01846	$0.01846
Haiku 4.5	$0.00923	$0.00923

Measured 2mo ago against content hash 52bb866229b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

algochains-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 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.

AGENTS.md · 607 lines

How it starts

The opening of the file, as written. The whole thing — 607 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AlgoChains MCP Server — Agent Context

This file is the primary context document for IDE agents (Cursor, Claude, Windsurf, Codex, etc.). Read it before invoking any AlgoChains tool so you don't guess at tool names, auth requirements, or safety rules.

QUICK START FOR NEW USERS / AGENTS

If the user has no credentials, says "get started", "explore", "try it", or "get familiar":

Call get_started() first — returns a zero-auth onboarding menu (no API key needed)

Offer the AlgoChains virtual paper account as the recommended first step — free hosted paper trading, copy-trade MNQ signals, zero broker credentials

Walk them through the subscriber funnel: get_checkout_url → accept_subscriber_terms → join_bot → get_my_portfolio

Do NOT suggest Tradovate, Alpaca, or any broker credentials unless the user explicitly says they want live trading

The subscriber virtual paper path unlocks 16 real subscriber tools — real signals, real P&L tracking, self-directed paper orders — with only a sub_live_… key. No broker account. No real money. A $50k virtual paper account is auto-provisioned on signup.

1. Identity and Transport

What this server is: An MCP server that connects your AI assistant to trading infrastructure — market data, backtesting, ML regime detection, broker connectivity, and live-bot operations across 535 tools in 21 domains.

Three transport entry-points:

Transport	Entry-point	Best for
stdio	`algochains-mcp` CLI (default)	Cursor, Claude Desktop, Windsurf
HTTP bridge	`moltbook/http_bridge.py` port 8090	algochains.ai platform, Command Center
SSE	`moltbook/sse_server.py` port 8765	Streaming / event-driven clients

Claude.ai web/mobile connector rule: never tell a user to paste localhost, 127.0.0.1, 0.0.0.0, a phone LAN address, or a Tailscale-only 100.x URL into a Claude.ai custom connector. The local PyPI package is stdio and works for desktop clients that can spawn a local process. Claude.ai web/mobile calls remote MCP servers from Anthropic's infrastructure, so it needs a public https://.../mcp endpoint. Use algochains-mcp-http --host 127.0.0.1 --port 8080 behind a secure HTTPS tunnel for testing, or a hosted HTTPS bridge for production.

Read the full file on GitHub · 607 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.

2mo ago Changed · +17 tokens per session 52bb866229b9
2mo ago First seen · 607 lines · 9,214 tokens per session scan A 22166d6ad400

Subscribe to this mod's changes

algochains-mcp-server AGENTS.md is an instructions file published in the GitHub repository AlgoChains/algochains-mcp-server (1 stars, last pushed 1mo ago), licensed MIT. It adds 9,231 tokens to every session, about $0.0369 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.

algochains-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
algochains-mcp-server AGENTS.mdAlgoChains/algochains-mcp-server	Instructions file	1	1mo ago	MIT	A	9,231	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	5,516	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
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

algochains-mcp-server: Instructions file for Codex