meta-trader-mcp@1.2.2
CAUTION· install onlyPublisher claims: "A production-grade, cross-platform MCP Server for MetaTrader 5" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
MT5_PASSWORDMTM_REST_TOKENConfiguration, not credentials: MT5_LOGIN, MT5_SERVER, MTM_BACKTESTS_DIR, MTM_OPTIMIZATIONS_DB, MTM_REPORTS_DB, MTM_REPORTS_DIR, MTM_SETUP_PACKAGE_SPEC, MTM_WINE_BINARY, MTM_WINE_PREFIX, WINEPREFIX- Where it talks to
- no vendor host named in the codeAlso apple.com, astral.sh, yahoo.com, nasdaq.com, marketaux.com, finnhub.io, faireconomy.media, financialmodelingprep.com, alphavantage.co, polygon.io, python.org, pythonhosted.org — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names apple.com, astral.sh, yahoo.com, nasdaq.com, marketaux.com, finnhub.io, faireconomy.media, financialmodelingprep.com, alphavantage.co, polygon.io, python.org, pythonhosted.org as well as its own vendor. The guard injects MT5_PASSWORD, MTM_REST_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Hidden zero-width characters detected; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
if self._version_synced or not getattr(self._wine_settings, "bridge_auto_update", True):Fix: Pin versions and sources; vendor anything fetched at install time.subprocess.run(["launchctl", "bootout", f"gui/{uid}/{BRIDGE_LABEL}"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.grep terminal/tester logs, check/kill MT5 processes, diagnose a backtest run,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.line = raw.strip().lstrip("")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.bridge_auto_update: bool = TrueFix: Pin versions and sources; vendor anything fetched at install time.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["launchctl", "unload", "-w", str(plist_path)], capture_output=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["launchctl", "kickstart", "-k", f"gui/{uid}/{BRIDGE_LABEL}"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.env_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Load settings from env/.env, applying explicit CLI ``overrides``.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.environment / ``.env`` (gitignored) and are never logged (see SECURITY.md);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.boot = subprocess.run(["launchctl", "bootstrap", f"gui/{uid}", str(plist)],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["launchctl", "load", "-w", str(plist_path)], capture_output=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self._terminal_proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# set MTM_BRIDGE_AUTO_UPDATE=false to manage the bridge version manually.Fix: Pin versions and sources; vendor anything fetched at install time.# ./scripts/smoke.sh --destructive # also clean the tester cache / kill terminalFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# `.env.example` ships `MT5_LOGIN=` — treat the empty string as unset.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.self._bridge_proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["launchctl", "unload", str(plist_path)], capture_output=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["systemctl", "--user", "daemon-reload"], capture_output=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["launchctl", "load", "-w", str(plist)], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Runtime configuration — environment variables, ``.env`` and CLI flags.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary><b>Linux</b> (not yet maintainer-tested) — live MT5 via Wine</summary> 1. Install Wine and MetaTrader 5 into a prefix; log in once. 2. `pipx install meFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for meta-trader-mcp@1.2.2 as of 3d ago. This is the package itself, not its dependencies.
What would make this Verified
15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim shubhvisputek: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.