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.
npx agentmods add instructions/thefractalyst/metatradermcp/agents-mdgit clone --depth 1 https://github.com/TheFractalyst/MetatraderMCPWrote 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.
[](https://agentmods.dev/instructions/thefractalyst/metatradermcp/agents-md)<a href="https://agentmods.dev/instructions/thefractalyst/metatradermcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thefractalyst/metatradermcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00970 | $0.00970 |
| Opus 5 | $0.00485 | $0.00485 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
MetatraderMCP 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 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MetaTraderMCP - Agent Instructions
Overview
MQL4/MQL5 reference documentation MCP server with 4863 entries covering 100% of the official MQL5 and MQL4 documentation sitemaps.
Commands
Setup
python -m venv .venv
source .venv/bin/activate # macOS/Linux
pip install -e ".[dev]"
Index database
metatradermcp build
Run server
metatradermcp # stdio (default)
TRANSPORT=sse PORT=8080 metatradermcp # HTTP/SSE
Lint
ruff check . --line-length 120
Test
pytest tests/ -v
Architecture
- FastMCP 3.4 with FileSystemProvider for auto-discovery
- ChromaDB vector store (cosine, all-MiniLM-L6-v2, 384-dim)
- 3 composable lifespans: db | model | cache
- Circuit breaker on compiler and ChromaDB
- Hot cache for fast lookups
- Response capping at 80KB
- Error masking (no internal details leaked)
Compiler (gold-standard MetaEditor via SSH)
The mql_compile tool tries compilation methods in priority order:
- Local MetaEditor (
METAEDITOR_PATHenv var, or auto-detected Wine/CrossOver) - Remote SSH MetaEditor (
METAEDITOR_SSH_HOSTenv var) - RECOMMENDED for macOS - mql5-lsp (community Rust LSP, tree-sitter based) - fallback, catches syntax only
- Python pattern checks - fallback, catches MQL4->MQL5 migration issues
Setting up SSH compilation (recommended)
Requires a Windows host (or WSL) with MetaTrader 5 installed and SSH access:
# In .env or your shell environment:
export METAEDITOR_SSH_HOST=your-windows-host
The MCP auto-installs bin/mql_compile_remote.sh on the remote host on first use.
The helper script:
- Derives Windows paths from WSL paths (
/mnt/c/...->C:\\...\\) - Runs
metaeditor64.exe /compile:"path" /log:"path" - Reads the UTF-16LE log and converts to UTF-8 for parsing
Compiler accuracy comparison
+-------------------------+--------+-----------+
| Error type | LSP | MetaEdit |
+-------------------------+--------+-----------+
| Missing semicolon | YES | YES |
| Unresolved includes | YES | YES |
| Undeclared identifiers | NO | YES |
| Wrong parameter count | YES | YES |
| Type mismatches | NO | YES |
| MQL4-isms in MQL5 | YES* | YES |
+-------------------------+--------+-----------+
* = caught by Python pattern checks, not the LSP itself
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.
- 5d ago First seen · 112 lines · 970 tokens per session scan A 84afbe495e3c
MetatraderMCP AGENTS.md is an instructions file published in the GitHub repository TheFractalyst/MetatraderMCP (2 stars, last pushed 8d ago), licensed MIT. It adds 970 tokens to every session, about $0.0049 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.
Other instructions, from other repositories
Skill_Seekers CLAUDE.md
Instructions for yusufkaraaslan/Skill_Seekers, covering claude.md, project overview, essential commands, required before running tests or cli (src/ layout) and run all tests (never skip - all must pass before commits).
docs-to-pdf CLAUDE.md
Claude Code instructions for jean-humann/docs-to-pdf, covering claude development guide for docs-to-pdf, project overview, development environment setup, using mise (recommended) and install mise (if not already installed).
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
slideops CLAUDE.md
Claude Code instructions for glukicov/slideops, covering claude.md, what this repository is, commands, the demo deck's citations must still match this repo and the citation mechanism (the core idea).
backend.ai AGENTS.md
AGENTS.md instructions for lablup/backend.ai, covering ai coding agent guidelines, document structure (agents.md / knowledge.md), writing style, document index and absolute rules (global).
mempalace AGENTS.md
AGENTS.md instructions for MemPalace/mempalace, a project described as: The best-benchmarked open-source AI memory system. And it's free.