-OS-Agent-MCP-Server
server that gives an LLM agent a small set of OS-level tools: - Search files and list directory contents. - Read and write UTF-8 text files. - Move and delete files or directories. - List likely terminal processes. - Launch a new terminal in a chosen folder.
Caution. Specific findings reduced this grade. They are listed on the page. 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
ikhlas-sayyed
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.
search_filesFind files below a directory using a glob such as '*.py' or 'README*'.
list_directoryList immediate children with their type and size.
read_text_fileRead a UTF-8 text file, capped to keep tool responses manageable.
write_text_fileCreate a UTF-8 text file, refusing to overwrite unless asked explicitly.
move_pathMove a file or directory within the configured local roots.
delete_pathDelete a file, or an empty directory unless recursive=true is provided.
list_open_terminalsList likely terminal processes currently running on this machine.
launch_terminalOpen a new terminal in a directory and optionally run one command.
MCP_ALLOWED_ROOTSTool 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
8/8 tools missing one or more hints — search_files (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_directory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read_text_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +5 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.
Destructive tools are labelled
1 tool perform destructive updates without destructiveHint — delete_path deletes at line 106 (shutil.rmtree(target))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — list_open_terminals (line 119: result = subprocess.run(command, capture_output=True, text=True, check=True))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tool test coverage
3/8 tools referenced in tests (38%)
Write tests that reference each tool by name so every tool has at least one test.
Tool description accuracy
list_open_terminals: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
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/ikhlas-sayyed/-os-agent-mcp-server)?variant=verified from the 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