mcpjail@0.1.0
VERIFIED· not startedPublisher claims: "The flight recorder & firewall for MCP tool calls." 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 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 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 2026-11-11 and scored it 85/100 (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
assert data["mcpServers"]["remote"] == {"url": "https://example.com/mcp"}Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."items": ["xoxb-123456789-abcdefghij"],Fix: Never read or enumerate credential locations; accept a documented environment variable instead.rules=[Rule(id="env", action="deny", server="*", resource_uri="file://**/.env*")],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."note": "use AKIAIOSFODNN7EXAMPLE for s3",Fix: Never read or enumerate credential locations; accept a documented environment variable instead.from mcpjail.proxy.http_proxy import HttpProxyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# Drop the background jobs from the job table so cleanup's kill doesn't printFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.match: { server: "*", resource_uri: "file://**/.env*" }Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert pol.evaluate(_call(tool="write_file", args={"path": "/etc/passwd"})).blockedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.["policy", "explain", "--policy", str(p), "--tool", "write_file", "--arg", "path=/etc/passwd"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.[ -n "$PX_PID" ] && kill "$PX_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.blocked = pol.evaluate(_call(method="resources/read", resource_uri="file:///home/u/.env.local"))Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.[ -n "$UP_PID" ] && kill "$UP_PID" 2>/dev/null || trueFix: 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 mcpjail@0.1.0 as of 4d ago. This is the package itself, not its dependencies.