terminal-use-mcp
Local + remote terminal interaction control MCP Server. Lets AI agents control interactive TUI programs the way a human would.
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
HLH2023
Source: Glama
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.
ComSpecSSH_AUTH_SOCKSSH agent socket path (discovered automatically if not set; see ssh-auth.ts discovery chain)TERMINAL_USE_ALLOW_INLINE_SSH_TARGETSSet to 1 to allow inline SSH host specification in tool calls _(not set — denied)_TERMINAL_USE_CONFIG_DIROverride XDG config directory See XDG/platform defaults belowTERMINAL_USE_CONFIG_FILEOverride config.json file path <config-dir>/config.jsonTERMINAL_USE_DATA_DIROverride XDG data directory (artifact, session data) See XDG/platform defaults belowTERMINAL_USE_HOSTS_CONFIGPath to SSH host profiles configuration file ~/.config/terminal-use-mcp/hosts.jsonTERMINAL_USE_LOG_LEVELLog verbosity: debug, info, warn, error infoTERMINAL_USE_TMUX_PATHIf tmux is not on PATH, set to its absolute or relative path.TERMINAL_USE_WORKSPACE_ROOT"": "<your-project-path>",TUMCP_TEST_KEY_PASSPHRASETUMCP_TEST_SSH_PASSPHRASEXDG_CONFIG_HOMEXDG config home — app appends terminal-use-mcp/ Linux, macOSXDG_DATA_HOMEXDG data home — app appends terminal-use-mcp/ Linux, macOSXDG_RUNTIME_DIRXDG runtime directory (used for SSH agent socket discovery) LinuxTool 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
29/29 tools missing one or more hints — terminal.attach (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); terminal.cleanup (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); terminal.events (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +26 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.
Tool inputs are validated
24/29 tool handlers declare input schemas (83%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Shell command execution
11 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
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/hlh2023/terminal-use-mcp)?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