agentic-windows-mcp@0.9.9
VERIFIED· not startedPublisher claims: "Agentic Windows MCP - an MCP server that gives AI agents full, safe control of a Windows PC: desktop automation, remote computer control, browser DevTools inspection, and remote software development." 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 codeAlso microsoft.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 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.
What changed since 0.9.3
vet-skills diff agentic-windows-mcp 0.9.3 0.9.9This version reaches for something 0.9.3 did not: 1 new host (microsoft.com). Compared from the two recorded runs, not from source.
- New hosts
- microsoft.com
0.9.3 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 2026-11-15 and scored it 87/100 (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
mkcert = subprocess.run(["where", "mkcert"], capture_output=True).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(["schtasks", *args], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.with subprocess.Popen(*popenargs, **kwargs) as process:Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.install = subprocess.run(["mkcert", "-install"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.| ChatGPT | HTTP connector (Developer mode) | Developer mode must be enabled |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.ChatGPT supports MCP through **Developer mode / Connectors**:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.ChatGPT supports MCP through **Developer mode / Connectors**:Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.logger.debug('Other exception occurred, attempting to kill process...')Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return f"Access denied to kill PID {pid}. Try running as administrator."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Process tool — list and kill running processes."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.return "Error: Provide either pid or name parameter for kill mode."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.| ChatGPT | HTTP connector (Developer mode) | Developer mode must be enabled |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.1. Settings → Connectors → enable Developer mode → *Create* a new connector.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.1. Settings → Connectors → enable Developer mode → *Create* a new connector.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.1. Settings → Connectors → enable Developer mode → *Create* a new connector.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.…nalytics): @mcp.tool( name="Process", description='List and kill running processes. Keywords: task manager, running tasks, kill, terminate, stop …Fix: 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 agentic-windows-mcp@0.9.9 as of 7d ago. This is the package itself, not its dependencies.