3commas-mcp CLAUDE.md

3commas-mcp CLAUDE.md is an instructions file for Claude Code from severity1/3commas-mcp. It costs 487 tokens per session, scanned A, original, MIT.

Project instructions for developing a 3Commas MCP server, which connects an AI agent to the 3Commas cryptocurrency-trading service. They define setup, API testing, code quality checks, and safety rules.

In plain words
What is it for?
Use them to implement or test 3Commas API endpoints, authentication, rate limits, data models, tool handlers, error handling, formatting, linting, and type checking.
Why use it?
They make API behavior and trading operations easier to validate before implementation. They also require input validation, error handling, privacy-safe examples, and checks for code quality.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/severity1/3commas-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/severity1/3commas-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 3commas-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/severity1/3commas-mcp/claude-md.svg)](https://agentmods.dev/instructions/severity1/3commas-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/severity1/3commas-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/severity1/3commas-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 487 This file is loaded in full into every session.
When invoked 487 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00487 $0.00487
Opus 5 $0.00244 $0.00244
Sonnet 5 $0.00097 $0.00097
Haiku 4.5 $0.00049 $0.00049

Measured 5d ago against content hash 2339f98abe69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

3commas-mcp 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 5d 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 · 40 lines

What it actually says

3Commas MCP Development

Context: 3Commas MCP server development with trading safety focus

Essential Commands

  • Setup: uv sync && uv pip install -e .
  • API Testing: python scripts/test_api.py <endpoint> (mandatory before implementation)
  • Quality Checks: uv run -m black . && uv run -m ruff format . && uv run -m ruff check . && uv run -m mypy .
  • Planning: Use /plan <api-identifier> for systematic implementation workflow

Core Principles

  • Trading safety first - Validate operations before execution
  • Script validation mandatory - Always test APIs before implementation
  • Pattern compliance - Follow @docs/PATTERNS.md exactly
  • Privacy protection - Use dummy data ONLY when documenting (bot ID 12345678, $245.67 profit)
  • KISS & DRY - Keep implementations simple and avoid code duplication

Component Focus

  • API layer - HMAC-SHA256 auth, rate limiting (100/min global, 120/min deals, 40/10s smart_trades)
  • Model layer - Pydantic validation with Field() constraints and enum integration
  • Tool layer - @handle_api_errors decorator with filter_response() application
  • Utils layer - Error handling, response filtering, authentication utilities

Required Workflow

  1. Test endpoint: python scripts/test_api.py <endpoint> (check token limits)
  2. Validate parameters: Use script-validated parameter names only
  3. Follow patterns: Implement using established patterns in @docs/PATTERNS.md
  4. Update documentation: All 4 layers (status, tools, models, conversations)

Integration Requirements

  • All tools use @handle_api_errors decorator
  • All responses use filter_response() before return
  • All models inherit from APIRequest with response_filter field
  • Authentication handled automatically via api_request()

Available Infrastructure

  • FastMCP Server: server.py with tool registration
  • Rate Limiting: Automatic endpoint detection and limit application
  • Token Optimization: Response filtering (85% reduction on display mode)
  • Error Handling: Consistent {"error": "message"} formatting
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. 5d ago First seen · 40 lines · 487 tokens per session scan A 2339f98abe69

Subscribe to this mod's changes

3commas-mcp CLAUDE.md is an instructions file published in the GitHub repository severity1/3commas-mcp (3 stars, last pushed 1y ago), licensed MIT. It adds 487 tokens to every session, about $0.0024 per session on Opus 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

Other instructions, from other repositories