Create a Task handle for MCP Tasks with a stable client_request_id so lost creation responses are safe to retry.
MIT
649,985 tools. Updated 2026-10-11 04:06
"Asynchronous command execution for OpenCode terminal tasks" matching MCP tools:
- Execute commands in a terminal window, read structured output, and wait for patterns or quiet periods. Use 'run' for complete command execution with result.MIT
- Run a command on a remote host via SSH without blocking. Use the returned command ID to check status, get output, or interrupt execution.MIT
- Generate an encrypted deployer keystore for Ethereum deployments. Returns step-by-step terminal instructions for manual execution.MIT
- Retrieve the full plain-text output of a recorded terminal command along with its command line, exit code, cwd, and timing by command ID or relative position.MIT
- Execute commands in a visible terminal window by sending text input to a specified session, allowing real-time command execution and interaction with the terminal environment.MITDestructive
Matching MCP Servers
execution-run-mcpofficial
AlicenseAqualityNot gradedmaintenanceEnables AI agents to interact with the Execute.run bot API for managing Shell balances, transferring funds, and executing LLM requests. It provides tools for identity verification, transaction tracking, and performing compute tasks through the Execute.run platform.6-- AlicenseAqualityFmaintenanceAn MCP server that enables secure terminal command execution, directory navigation, and file system operations through a standardized interface for LLMs.10110 PyPI95MIT
Matching MCP Connectors
I run shell commands on your private cloud environment (bash, sh, zsh)
Provision an OpenCode workbench and MCP stack on any Linux box, local or over SSH.
- Run a command with adjusted CPU scheduling priority. Use positive niceness values to lower priority for background tasks, reducing CPU impact.MITDestructive
- Dispatch a task to a Clanker backend (codex, opencode, grok) and wait for terminal result. Polling avoids timeouts on long tasks.MITDestructive
- Submit a command intent for an agent in a round, recorded for backend validation and subsequent execution. Inspect the command spec first to ensure a valid payload.MIT
- Start a new opencode coding session to obtain a session ID and project directory for subsequent agent messages.MIT
- Gracefully stop the opencode server and close all active sessions when done. Ensures clean shutdown after completing opencode tasks.MIT
- Cancel a running background task by providing its task ID. Pending tasks transition to cancelled; terminal tasks remain unaffected.MITDestructive
- Run a shell command in a Google Colab terminal and wait for its completion. Designed for quick commands, not long-running tasks.Apache 2.0
- Send text or commands to a VS Code terminal. Use getTerminalOutput to verify execution results.MITDestructive
- Run commands that persist after terminal exit by ignoring hangup signals. Use for long-running background tasks that need to survive terminal closure.MITDestructive
- Poll an execution until it reaches a terminal state or timeout. Returns early with waiting status if the execution pauses on a Wait node, enabling asynchronous workflow handling.MIT
- Waits for a regex pattern to match terminal output, enabling scripted command sequences to pause until expected output appears. Returns match status and matched text.MIT
- Returns a terminal command for GitHub authentication for the figure library, without launching a browser or login process.MIT
- Launch a new terminal session with virtual X11 display to run commands and capture visual output for AI agents interacting with terminal applications.Apache 2.0
- Approve or deny terminal commands that require permission when using manual approval mode in the Host Terminal MCP server for safe command execution.Apache 2.0
- Drop terminal (done/failed/dead) tasks from a queue for cleanup, keeping in-flight ones. Returns count of removed tasks.MIT