remotify-mcp
Run remote shell commands from AI assistants, with optional human approval.
remotify-mcp is an Apache-2.0 local stdio MCP server that connects AI assistants to remote shell workflows through an HTTP relay. The local MCP process runs with Node.js and can be launched using npx remotify-mcp. The remote operator starts a curl-and-bash listener, so no inbound SSH port or permanent agent installation is required. Version 0.6.2 exposes three tools: remote_exec, remote_session_info, and remote_session_reset. Supervised mode asks the remote operator to approve each command; optional auto mode executes commands without per-command confirmation. Commands run with the privileges of the user who starts the listener. The relay can be self-hosted using the published repository, and the default public relay is https://relay.remotify.run. No account or API key is required to create a relay session, but its private session key grants access to that session. The relay temporarily stores queued commands, results, and push history until explicit deletion or idle expiry; it is not an execution sandbox. Verification covered the public source and license, the npm package matching the inspected server source, live relay health, and local MCP initialization, three-tool discovery, and rejection of an empty command. No remote listener was attached and end-to-end remote command execution was not tested.
Best for agent capabilities
Useful in agent tasks
Overview
When to use remotify-mcp
remotify-mcp is listed for Code Execution workflows. remotify-mcp is an Apache-2.0 local stdio MCP server that connects AI assistants to remote shell workflows through an HTTP relay. The local MCP process runs with Node.js and can be launched using npx remotify-mcp. The remote operator starts a curl-and-bash listener, so no inbound SSH port or permanent agent installation is required. Version 0.6.2 exposes three tools: remote_exec, remote_session_info, and remote_session_reset. Supervised mode asks the remote operator to approve each command; optional auto mode executes commands without per-command confirmation. Commands run with the privileges of the user who starts the listener. The relay can be self-hosted using the published repository, and the default public relay is https://relay.remotify.run. No account or API key is required to create a relay session, but its private session key grants access to that session. The relay temporarily stores queued commands, results, and push history until explicit deletion or idle expiry; it is not an execution sandbox. Verification covered the public source and license, the npm package matching the inspected server source, live relay health, and local MCP initialization, three-tool discovery, and rejection of an empty command. No remote listener was attached and end-to-end remote command execution was not tested. Consider it when an agent needs this capability through a documented service boundary instead of custom infrastructure maintained inside the application.
In 4agent's task model, the product maps to code execution. That makes it a candidate for workflows that build and deploy software.
Integration checklist
- Access: confirm the none authentication flow, credential scope, rotation process, and whether calls can be attributed to a user or service identity.
- Client support: no SDK is recorded, so verify the HTTP API or another supported integration path.
- Automation: OpenAPI is not currently recorded, MCP is listed as available, and CLI support is not currently recorded. Confirm each requirement in the provider's current documentation.
- Operations: test rate limits, timeouts, retry safety, error payloads, logs, data retention, and the current free-tier and paid pricing model with production-like volume.
Sources and verification
Use these primary sources to verify current behavior before making an implementation or purchasing decision. Product capabilities, limits, and prices can change after a 4agent listing is reviewed.