musu_remote_mcp_win
Dockerless Windows remote development MCP with OAuth, checkpoints, durable jobs, and native service support
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
yellowhama
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
exec_commandRun an unrestricted shell command on the host. The command inherits the MCP server's full OS permissions, environment, filesystem, and network access. A successful start always returns a process session ID, current process state, and retained output; poll a running process with read_process or write…
run_scriptWrite a supplied script to a temporary executable file and run it with Bash, sh, Node.js, Python, or an arbitrary interpreter. Execution is unrestricted and has the MCP server's full host permissions. A successful start always returns a process session ID, current process state, and retained output.
write_stdinWrite text to an existing process session, optionally close stdin, then return current process state and retained output with sequence numbers greater than afterSeq.
read_processPoll a managed process for output and terminal state. Pass the previous nextSeq as afterSeq to receive only newer output.
terminate_processSend a signal to a managed process tree. When graceMs is greater than zero, SIGINT and SIGTERM escalate to SIGKILL if the process is still running after the grace period. The call may return while escalation is still pending.
list_processesList running and recently completed process sessions.
list_directoryList any host directory. Recursive listing does not follow directory symlinks.
stat_pathReturn metadata for any file, directory, or symbolic link.
read_fileRead a bounded chunk of any host file as UTF-8 text or base64. UTF-8 reads preserve character boundaries and may exceed maxBytes by up to three bytes only when one complete character would otherwise not fit. Continue with nextOffset until eof=true.
write_fileCreate, overwrite, or append to any host file using UTF-8 or base64 content.
replace_in_filePerform an exact text replacement in a UTF-8 file. By default exactly one occurrence must exist, preventing ambiguous edits.
apply_patchValidate and apply a standard unified diff with git apply. Paths are unrestricted and --unsafe-paths is enabled.
upload_fileWrite a base64 file chunk at an exact byte offset. Use truncate=true for the first chunk of a replacement upload, then continue with nextOffset.
download_fileRead a file chunk as base64. Continue with nextOffset until eof=true.
make_directoryCreate any host directory.
copy_pathCopy a file or directory anywhere on the host.
move_pathMove or rename a file or directory anywhere on the host.
remove_pathPermanently remove any host file or directory. This operation is not restricted to a workspace and does not use trash.
chmod_pathChange Unix permission bits on any host path.
hash_fileCalculate a digest for any host file, useful for transfer verification.
MCP_WINDOWS_EVENT_LOG_SOURCESystemRootTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
20/20 tools missing one or more hints — exec_command (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); run_script (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); write_stdin (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +17 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/yellowhama/musu_remote_mcp_win)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check