tradeiq-lab-mcp@0.4.1
VERIFIED· not startedPublisher claims: "MCP server for backtesting Indian stock strategies with keyless Yahoo data: write a strategy, backtest it, export a report." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified 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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso nseindia.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
detail = _tail((self._dir / "worker.log").read_bytes()[-2 * _OUTPUT_TAIL:])Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.redirector), and a host job object that permits breakaway. It does NOT survive a tree killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.A job folder holds ``job.json`` (the state below), the runner's inputs written by the server processFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."""A finite float rounded to kill float residue, else None."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.POSIX: ``start_new_session=True`` (own session and process group, so ``kill_tree`` can kill the group);Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.child = subprocess.Popen(list(argv), start_new_session=True, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.``Popen`` so the caller can poll finished trials, kill the worker and keep partial results.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.except Exception: # a missed beat is retried next time; never kill the runner over itFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."os.rmdir os.mkdir os.chmod os.chown os.chflags os.lchflags os.lchmod os.link os.symlink "Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.subprocess.run([exe if os.path.isfile(exe) else "taskkill", "/PID", str(pid), "/T", "/F"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.exec(code, namespace)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."os.system os.startfile os.startfile/2 os.kill os.killpg os.fork os.forkpty os.remove os.rename "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.child = subprocess.Popen(list(argv), creationflags=flags, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.``store`` holds job state in ``<workspace>/jobs/<job_id>/`` (``job.json``, ``params.json``, the inputs,Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.accept(run.poll()) # a trial that finished just before the kill still countsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Files: ``strategy.py`` (byte for byte), ``candles.npz`` + ``config.json`` (the sandbox input format ofFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self._proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.child = subprocess.Popen(list(argv), creationflags=flags | CREATE_BREAKAWAY_FROM_JOB, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.(``params.json``, ``strategy.py``, ``candles.npz``, ``config.json``; see ``write_job_inputs``), the runner'sFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.``cancelled``), else mark it ``cancelled`` and kill the runner's process tree, but ONLY a processFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.