zcode-mcp
Related Servers
Alternatives to zcode-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceDelegates autonomous coding tasks to Z.ai's GLM models with a genuine agent loop, file operations, and verification via git and real process results.13 npmMIT
- AlicenseAqualityCmaintenanceEnables Codex/ChatGPT to coordinate OpenCode agents, managing tasks, sessions, parallel execution, and project context through 25 local tools.254 npm1MIT
- AlicenseNot gradedqualityBmaintenanceEnables ChatGPT conversations to directly inspect local workspaces and delegate coding tasks to a local Codex agent, with controlled concurrency, reusable sessions, and task/usage tracking.1,249 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients like Claude Code to delegate coding tasks to the local Cursor Agent CLI, with persistent per-workspace sessions that resume across calls.12 npmMIT
- AlicenseAqualityBmaintenanceEnables ChatGPT Desktop and Codex to delegate substantial work to a locally installed Grok Build agent. Supports consultations, background builder/tester jobs, cancellation, session discovery, and transcript export.7MIT
- AlicenseAqualityBmaintenanceEnables Codex to control CodeBuddy Code through the Agent Client Protocol, including launching local or SSH sessions, sending prompts, handling permissions, and managing session lifecycle.51MIT
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: zcode_run executes a task, zcode_check verifies backend health, and zcode_sessions lists past sessions. There is no overlap or ambiguity between them.
All tools share the consistent 'zcode_' prefix and snake_case convention. However, 'zcode_sessions' is a noun rather than a verb-based name, deviating slightly from the verb-oriented pattern of 'zcode_run' and 'zcode_check'.
Three tools form a well-scoped set for a coding-agent management server. Each tool serves a distinct and necessary function without bloat or redundancy.
The core workflow (check backend, run tasks, list sessions) is covered, and session_id reuse enables follow-ups. A minor gap exists in having no dedicated tool to inspect a single session's full details, but this is workable via the existing surface.