Skills/PyPI/tmodloader-mcp

tmodloader-mcp@0.7.1

VERIFIED· not started

Publisher claims: "Drive a running tModLoader instance: launch it, ask it questions, photograph it, and read its state back." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher musharna · publishing for 180 daysInstalls 345Last detonated 2 h ago
$claude mcp add tmodloader-mcp -- uvx tmodloader-mcp
WatchReport an issue

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 code
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.

$vet-skills run --net declared -- uvx tmodloader-mcp

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 2026-11-19 and scored it 80/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.3sprocessdependency install exit 1 ·
0.3sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedsrc/tmodloader_mcp/build.py:118 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/tmodloader_mcp/session.py:2378 · Python subprocess execution detectedsubprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/tmodloader_mcp/session.py:2662 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/live_race_check.py:159 · Python subprocess execution detecteddone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/tmodloader_mcp/session.py:2245 · Python subprocess execution detectedsubprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/tmodloader_mcp/session.py:248 · Python subprocess execution detecteddone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/tmodloader_mcp/api.py:250 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/live_race_check.py:106 · Python subprocess execution detectedsubprocess.Popen(_client_join_cmd(cfg, PORT_B, PLAYER_B), **spawn)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/tmodloader_mcp/session.py:2235 · Python subprocess execution detectedsubprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/live_race_check.py:88 · Python subprocess execution detectedsubprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:356 · Collapsed <details> block carrying instructions<summary><code>TMODLOADER_MOD_NAME</code> — when the derived name is wrong, and what the name keeps apart</summary> `TMODLOADER_MOD_NAME` is the mod's **internaFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandsrc/tmodloader_mcp/session.py:64 · Process kill command — agent can terminate processes#: FILETIME. The creation time is what pins a kill to the PROCESS rather thanFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_session_lifecycle.py:107 · Process kill command — agent can terminate processes`unkillable` is how a kill that does not take is expressed: taskkill stillFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_mcp_protocol.py:407 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesbad = await session.call_tool("read_capture", {"name": "../../../etc/passwd"})Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandtests/test_session_lifecycle.py:585 · Process kill command — agent can terminate processesA teardown-on-failure that also fired on success would kill the game theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_captures.py:59 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"../../../etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_logs.py:234 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslogs.read_since(tmp_path, "../../etc/passwd", offset=0)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/tmodloader_mcp/saves.py:73 · Process kill command — agent can terminate processes#: finished, so a restore that dies partway - a /mnt/c lock, a kill - is onFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/tmodloader_mcp/session.py:97 · Process kill command — agent can terminate processesold pid-only behaviour rather than refusing to kill what this sessionFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_live_check_contract.py:439 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/tmodloader_mcp/session.py:7 · Process kill command — agent can terminate processessignals. And a teardown must kill ONLY what this session started: a developerFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_mcp_protocol.py:442 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`capture://../../../etc/passwd` fails to match the URI template and comesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_log_files.py:111 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfor escape in ["../../secrets.log", "Old/2026-07-29-4.zip", "/etc/passwd"]:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiontests/test_log_watch.py:149 · File type combined with upload action — agent may exfiltrate local data files_write(tml, "client.log", "a long first run with plenty of output\n")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathstests/test_captures.py:78 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""`Path(dir) / "/etc/passwd"` is `/etc/passwd` — joining does not containFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiontests/test_addressing.py:1013 · File type combined with upload action — agent may exfiltrate local data files(tmp_path / f"{stem}-server.txt").write_text("hooks-seen: PostUpdateWorld\n")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandsrc/tmodloader_mcp/session.py:2289 · Process kill command — agent can terminate processes# `stop` will later kill it. The creation stamps recorded beside the pidsFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_session_lifecycle.py:100 · Process kill command — agent can terminate processes"""A process table a kill can actually change.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/tmodloader_mcp/session.py:271 · Process kill command — agent can terminate processesTHIS form goes on to act on the answer - refuse a launch, kill a pid,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/tmodloader_mcp/server.py:1626 · Process kill command — agent can terminate processeskill was aimed at. If any survive, this FAILS rather than answering with aFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_mcp_protocol.py:460 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"capture://../../../etc/passwd", # refused by routing - see docstringFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandtests/test_session_lifecycle.py:1116 · Process kill command — agent can terminate processesassert windows.aimed == [4808], "it never even tried to kill it"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_session_lifecycle.py:1096 · Process kill command — agent can terminate processesdied between the listing and the kill exits non-zero, and that is theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_live_check_contract.py:382 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_live_check_contract.py:381 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈64 tok
1 file · 61 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

No advisories in OSV for tmodloader-mcp@0.7.1 as of 2 h ago. This is the package itself, not its dependencies.