# ssh-run Executes a command on a remote host via SSH. WARNING: This runs commands on a remote machine. Ensure the host and command are correct before executing. Returns structured output with stdout, stderr, exit code, and duration. Agent View of the PolicyLayer registry record for `ssh-run`. HTML page: https://policylayer.com/tools/io-github-dave-london-pare-search/ssh-run ## Facts - Tool: `ssh-run` - Server: Search (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-pare-search.md - Homepage: https://github.com/Dave-London/Pare - Risk category: Execute (High risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Rate-limited ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "ssh-run", "arguments": {} } } ``` ## Why ssh-run is rated High This tool executes arbitrary commands on remote systems via SSH. While not inherently destructive (depends on the command arguments), it represents Execute-category risk because it triggers external operations whose effects are argument-dependent and run on systems outside the immediate environment. From the tool's own definition: "Tool description explicitly states 'Executes a command on a remote host via SSH' and warns 'This runs commands on a remote machine.' Returns structured output including exit code and duration, confirming command execution semantics." ## Use case AI agents invoke ssh-run to trigger actions in Search. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Search: ```json { "version": "1", "default": "deny", "tools": { "ssh-run": { "limits": [ { "counter": "ssh-run_rate", "window": "minute", "max": 10, "scope": "grant" } ] } } } ``` ## Other tools on Search (201) - `branch` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/branch.md - `clean` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/clean.md - `package-clean` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/package-clean.md - `remove` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/remove.md - `reset` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/reset.md - `secret-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/secret-delete.md - `stash` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/stash.md - `tag` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/tag.md - `variable-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/variable-delete.md - `workspace` — Destructive — https://policylayer.com/tools/io-github-dave-london-pare-search/workspace.md - `add` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/add.md - `add-package` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/add-package.md - `ansible-galaxy` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/ansible-galaxy.md - `ansible-playbook` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/ansible-playbook.md - `api` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/api.md - `apply` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/apply.md - `audit` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/audit.md - `bazel` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/bazel.md - `biome-check` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/biome-check.md - `bisect` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/bisect.md - `black` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/black.md - `build` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/build.md - `bundle-exec` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/bundle-exec.md - `bundle-install` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/bundle-install.md - `check` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/check.md - `checkout` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/checkout.md - `cherry-pick` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/cherry-pick.md - `clippy` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/clippy.md - `cmake` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/cmake.md - `compose-build` — Execute — https://policylayer.com/tools/io-github-dave-london-pare-search/compose-build.md - …and 171 more: https://policylayer.com/tools/io-github-dave-london-pare-search.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-dave-london-pare-search · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-dave-london-pare-search