tracker-mcp@0.8.6
VERIFIED· not startedPublisher claims: "MCP server for your job-application tracker in Excel, CSV or Google Sheets: follow-ups, funnel, safe confirmed writes" 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
GOOGLE_APPLICATION_CREDENTIALSTRACKER_GOOGLE_TOKENor--client-secretConfiguration, not credentials: TRACKER_ALLOW_UNCONFIRMED, TRACKER_BACKUP_DIR, TRACKER_CONFIG, TRACKER_DIALOG_ONLY, TRACKER_GOOGLE_CLIENT, TRACKER_MCP_DEBUG, TRACKER_MCP_HOME, TRACKER_PATH, TRACKER_READ_ONLY- Where it talks to
- no vendor host named in the codeAlso google.com, claude.ai, claude.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 with a scoped credential, under the guard, and read the third-party hosts first. The code names google.com, claude.ai, claude.com as well as its own vendor. The guard injects GOOGLE_APPLICATION_CREDENTIALS, TRACKER_GOOGLE_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.
What changed since 0.8.4
vet-skills diff tracker-mcp 0.8.4 0.8.6In the sandbox, this version reached for nothing 0.8.4 did not. Compared from the two recorded runs, not from source.
0.8.4 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
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 86/100 (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
out = subprocess.run([sys.executable, "-m", "tracker_mcp.server", "--check"], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.forged2 = {**entry, "at": "2099-01-02T00:00:00", "backup": "../../etc/passwd", "tracker": t.store.label}Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.bad = subprocess.run([sys.executable, "-m", "tracker_mcp.server", "--check"], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, "-m", "tracker_mcp.server", "--tracker", str(book), "--config",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.for ch in "\U000e0069
\x85":Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."""Wire the shared MCPServer for HTTP with sign-in, and return (remote, ASGI app)."""Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.out = subprocess.run([sys.executable, "-m", "tracker_mcp.server", "--tracker", str(path), "--check"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, "-c", "import sys; from tracker_mcp.server import main; main(sys.argv[1:])",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.ex = subprocess.run([sys.executable, "-m", "tracker_mcp.server", "example"], capture_output=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.spec.loader.exec_module(ev)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.for text in ("ab", "ab", "a\U000E0069b", "ab", "ab"):Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.for ch in "\U000e0069
\x85":Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.run = lambda *a: subprocess.run([sys.executable, "-m", "tracker_mcp.server", *a], # noqa: E731Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.ev = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.run = lambda *a: subprocess.run([sys.executable, "-m", "tracker_mcp.server", *a], # noqa: E731Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.for text in ("👨👩👧", "🏳️🌈", "\U0001F3F4\U000E0067\U000E0062\U000E0073\U000E0063\U000E0074\U000E007F",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.path.write_bytes("Company;Role;Status;Date Applied\nAcme;EM;Applied;09/02/2026\n".encode())Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.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.