mcp-tracking@0.3.1
VERIFIED· not startedPublisher claims: "Local-first, self-hosted MCP server, HTTP API and Textual TUI dashboard to track long-running tasks of LLM agents in real time" 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
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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
CREDENTIALS_DIRECTORYTRACKING_TOKEN_FILEConfiguration, not credentials: RUNTIME_DIRECTORY, TRACKING_STATE_DIR, TRACKING_TEMPLATES_FILE, TRACKING_TTL_DAYS, TRACKING_TTL_RUNNING_H, XDG_RUNTIME_DIR, XDG_STATE_HOME- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard. It asks for CREDENTIALS_DIRECTORY, TRACKING_TOKEN_FILE and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-10 and scored it 82/100 (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 · 3 scenarios · 0 deviationsStatic findings
sudo ./deploy.shFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.log.info("kill session=%s pid=%s -> %s", sid, session.pid, note)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.sudo ./deploy.shFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.sudo -u "$OWNER" cp -p "$DIR/$f" "$STATE/$f"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.sudo -u "$OWNER" mkdir -p "$STATE"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Pour redeployer apres une mise a jour du code : sudo ./deploy.shFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.POST /sessions/{id}/kill (SIGKILL si pid + suppression)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.Popen(cmd, start_new_session=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.pid: Optional[int] = None # processus a signaler pour stop / killFix: 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
No advisories in OSV for mcp-tracking@0.3.1 as of 4d ago. This is the package itself, not its dependencies.