Skills/PyPI/mcp-write-gate

mcp-write-gate@0.2.0

VERIFIED· not started

Publisher claims: "Sits between an AI agent and its MCP servers. Reads pass, writes are checked against your lists, and a read-only server refuses every write." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher goran-revops · publishing for 49 daysInstalls 182Last detonated 4d ago
$claude mcp add mcp-write-gate -- uvx mcp-write-gate
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
API_TOKEN or --oauthConfiguration, not credentials: MCP_WRITE_GATE_CONFIG, MCP_WRITE_GATE_HOME, MCP_WRITE_GATE_RUN, MCP_WRITE_GATE_RUN_AS
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 API_TOKEN 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.

$vet-skills run --net declared -- uvx mcp-write-gate

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 2026-11-10 and scored it 81/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedmcp_write_gate/facts.py:119 · Python subprocess execution detecteddone = subprocess.run(self.command, input=json.dumps(request), capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Unicode escape sequence detectedmcp_write_gate/targets.py:13 · Unicode escape sequence detected — may contain obfuscated payloads_INVISIBLE = dict.fromkeys(map(ord, "\xad\u200b\u200c\u200d\u200e\u200f\u2060\u2061\u2062\u2063\ufeff"), None)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Privileged sudo commandmcp_write_gate/proxy.py:41 · Privileged sudo command — agent may execute with elevated privileges# Needs a sudo rule "<gate user> ALL=(<run_as>) NOPASSWD:SETENV: ALL", as in the Docker image.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagemcp_write_gate/cli.py:418 · npx invocation of non-well-known package — may execute untrusted codeitem.epilog = "Put the command that starts the real server after --, for example: mcp-write-gate add mail --preset mail -- npx -y some-mail-mcp"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedmcp_write_gate/gate.py:450 · Python subprocess execution detectedsubprocess.run(spec["command"], input=json.dumps(note), text=True, capture_output=True, timeout=spec.get("timeout", 10), cwd=self.config.base)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_audit_hold.py:57 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesholds.get("../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_http.py:28 · Python subprocess execution detectedprocess = subprocess.Popen(args, cwd=str(ROOT), env={**os.environ, **(env or {})}, stderr=subprocess.PIPE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_hardening.py:175 · Python subprocess execution detecteddone = subprocess.run([sys.executable, "-c", script], capture_output=True, text=True, timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈72 tok
1 file · 45 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 mcp-write-gate@0.2.0 as of 4d ago. This is the package itself, not its dependencies.