hop-mcp
Related Servers
Alternatives to hop-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityDmaintenanceEnables parallel implementation of tasks using git worktrees, allowing you to create multiple variants of a solution, evaluate them side-by-side, and select the best one.2-
- AlicenseNot gradedqualityDmaintenanceA git worktree manager that enables AI agents to work on different branches simultaneously with automatic coordination, locking, and merge management. Supports creating, managing, and merging git worktrees with setup automation and conflict resolution.6 npm6MIT
- AlicenseCqualityBmaintenanceManages multiple AI CLI instances (Claude Code, Codex, Gemini, Cursor) in tmux sessions for parallel task execution, with optional git worktree support.90MIT
- AlicenseNot gradedqualityAmaintenanceManages isolated Git worktrees for each ZCode thread, enabling safe parallel development with automatic setup, snapshot-based removal, PR review, and background agent orchestration.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to manage Git worktrees by creating, listing, removing, and cleaning isolated workspaces through MCP tools.MIT
- FlicenseNot gradedqualityCmaintenanceEnables orchestrating multi-agent AI coding workflows with Git worktree isolation, parallel testing, and security scanning via the Model Context Protocol.-
TDQS
Scored across 14 tools
Every tool exists twice as an exact alias pair (hop_list/git_worktree_list, hop_start/git_worktree_create, hop_to/git_worktree_switch, etc.) with identical descriptions, so an agent cannot tell which to pick. Within a single prefix the purposes are distinct, but the deliberate duplication makes half the surface indistinguishable.
Two parallel naming schemes coexist for the same operations: a terse hop_* set and a git_worktree_* set, with mismatched verbs for the same action (hop_start vs git_worktree_create, hop_to vs git_worktree_switch, hop_end vs git_worktree_remove). Each scheme is internally readable, but mixing them for identical functionality breaks predictability.
The reported 14 tools collapse to only 7 unique operations, so half the count is redundant aliasing rather than earned surface. The underlying 7-tool scope (list, current, start, to, end, clean, open) is reasonable for a git worktree helper.
The set covers the core worktree lifecycle: enumerate, inspect current context, create, switch, remove, clean, and open in an IDE. Only secondary git worktree operations (prune, lock/unlock, move, repair) are absent, which agents can work around via raw git.