AgentDock MCP Harness
Related Servers
Alternatives to AgentDock MCP Harness
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityBmaintenanceEnables a ChatGPT Web conversation to act as a coding agent on a VPS, with project-bound chats, Git worktree isolation, live activity streaming, structured questions, and file/image exchange via MCP.-
- AlicenseNot gradedqualityAmaintenanceConnects ChatGPT Web to a self-hosted local coding workbench, enabling file editing, shell commands, Git/GitHub operations, multi-workspace management, code review, terminal processes, checkpoints, and optional Docker sandboxing.12MIT
- AlicenseNot gradedqualityAmaintenanceEnables ChatGPT to securely control remote development servers over OAuth-protected MCP, exposing workspace-bounded tools for file editing, command execution, Git operations, and running Codex or GitHub Copilot subagents.521 npm2MIT
- AlicenseCqualityAmaintenanceSecure agent coding runtime for local Git repos with policy enforcement, RBAC, sessions, approval workflow, and sandboxed writes, optionally connectable to ChatGPT via Secure MCP Tunnel.86MIT
- FlicenseNot gradedqualityCmaintenanceEnables ordinary ChatGPT web Chat to work directly on a local machine over a private MCP tunnel — reading and editing project files, running shell commands and tests, loading local skills, manipulating images, and driving Chrome — without spinning up a separate coding agent or additional model-generation API calls. It also supports multi-step task plans with persisted execution receipts and acceptance checks so results from real runs are returned to the conversation.-
- AlicenseNot gradedqualityBmaintenanceTurns ChatGPT web into a local coding agent, enabling file edits, shell commands, Git operations, patches, and process management through 40+ MCP tools.MIT
TDQS
Scored across 19 tools
Each tool is scoped to a distinct resource and action. Though process.cancel and task.cancel overlap in stopping processes, their descriptions clearly differentiate targeting a single process versus an entire task, making misselection unlikely.
All tool names follow a consistent domain.action pattern using lower_snake_case (e.g., task.create, file.read, approval.respond). The verb is always an imperative or descriptive action, and the dot prefix reliably indicates the resource domain, making the naming highly predictable.
With 19 tools, the set is slightly above the typical 3-15 range, but the variety of concerns (processes, tasks, files, git, audit, approvals) justifies the count. Each tool addresses a distinct operation without obvious redundancy, so it feels reasonably scoped rather than bloated.
The tool surface covers task lifecycle, file operations, git commit/diff, process management, audit, and approvals. However, there is no task.list or task.get endpoint to enumerate or query tasks by state; agents must know task IDs in advance, which is a notable gap in the otherwise comprehensive workflow.