overseer-nvim-mcp
Related Servers
Alternatives to overseer-nvim-mcp
- AlicenseAqualityAmaintenanceEnables AI assistants to control running Neovim sessions via RPC socket, supporting command execution, state inspection, and LSP actions. Automatically discovers Neovim instances and supports multi-instance management on Linux and macOS.1819 PyPI62MIT
- AlicenseAqualityBmaintenanceMake Neovim feel like Cursor. This MCP server gives an agent full control over the Neovim session it is running inside, including buffers, windows, diagnostics, LSP language intelligence, and terminals.23MIT
Related Servers
- FlicenseBqualityDmaintenanceAn MCP server that enables AI agents to control Neovim instances running in tmux sessions.12-
- AlicenseAqualityFmaintenanceMCP server for running external coding agents as background tasks inside Claude Code. Supports multiple backends including Codex, Grok, GLM, DeepSeek, and more.7MIT
- AlicenseNot gradedqualityAmaintenanceAn MCP server that bridges CLI coding agents like Claude Code, Codex, opencode, and Antigravity into any MCP client, enabling synchronous and asynchronous task execution, follow-up input, and a structured code review tool.103 npm1MIT
- AlicenseAqualityBmaintenanceAn MCP server that lets AI agents see, act on, and verify the rendered Neovim UI, like a Playwright for Neovim. It provides tools to launch/attach to Neovim, observe the screen, send input, and wait for conditions.8MIT
- AlicenseAqualityCmaintenanceMCP server that launches and supervises coding-CLI subagents (claude, opencode) in detached tmux windows, collapsing the ceremony of starting a TUI coding assistant into a single tool call.5MIT
- AlicenseNot gradedqualityAmaintenanceAn MCP server for orchestrating a fleet of CLI coding agents in isolated git worktrees. It exposes tools for spawning workers, sending instructions, reviewing diffs, and merging changes, with full terminal visibility.3 npm4MIT
TDQS
Scored across 7 tools
Each tool targets a distinct operation: listing tasks, listing templates, running, tailing output, restarting, stopping, and disposing. The descriptions reinforce the boundaries, e.g., tail's status line makes it unnecessary to call list_tasks just to check liveness.
All tools share the overseer_ prefix and follow a snake_case verb-first pattern. The two list tools include their noun (tasks/templates), while the task lifecycle operations use clear verbs (run, tail, restart, stop, dispose), which is consistent and predictable.
Seven tools is well-scoped for a task-runner server: discovery (list templates), listing (list tasks), execution (run), observation (tail), and lifecycle control (restart, stop, dispose). Every tool earns its place with no redundant overlap.
The surface covers the full task lifecycle: create/start (run), read/list (list_tasks, list_templates, tail), and delete/cleanup (dispose), plus control operations (restart, stop). The descriptions also explicitly account for short-lived commands being handled outside the server, so there are no obvious dead ends.