opencode-mcp
Related Servers
Alternatives to opencode-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that lets ChatGPT or any MCP client securely delegate coding tasks to a local Claude Code instance, with git checkpointing, approval gates, and structured results. Supports code review, test running, and rollback via simple tool calls.13 npmMIT
- AlicenseAqualityBmaintenanceA stdio MCP server that lets Codex Desktop/CLI delegate implementation tasks to Claude Code CLI with workspace validation, Git status checks, and session resume capabilities.24MIT
- FlicenseNot gradedqualityAmaintenanceMCP server for programmatic lifecycle management of Claude Code sessions, supporting list, create, read, send, fork, wait, and interrupt operations.1 npm1-
- AlicenseNot gradedqualityBmaintenanceAn MCP server that bridges Claude Desktop with Claude Code, allowing users to delegate tasks to Claude Code directly from Claude Desktop conversations, supporting both synchronous and background execution with session reuse.2 npmMIT
- AlicenseAqualityDmaintenanceMCP server that lets any agent or MCP host delegate tasks to Claude Code running headless, with tools for review, validation, analysis, and autonomous work.4154 npm2MIT
- AlicenseAqualityCmaintenanceAn MCP server and HTTP gateway that dispatches coding tasks to Claude Code, Codex, and Antigravity CLI sessions, keeps track of those sessions, and optionally runs an implement → review → verify loop against a real repository.6MIT
TDQS
Scored across 7 tools
Each tool maps to a distinct stage of the session lifecycle (start, reply, status, cancel, output, info, end), so most are easy to tell apart. The only friction points are opencode-cancel vs opencode-end (both stop a running turn, though only end deletes the session) and opencode-status vs opencode-output (both surface turn content, though output pages the full retained text).
All tools share a clear `opencode-` prefix in consistent kebab-case, which reads cleanly as a family. The only deviation is the bare `opencode` create tool and the fact that suffixes mix nouns (status, output, info) with verbs (reply, cancel, end), but the pattern is still predictable.
Seven tools is well-scoped for a coding-agent delegation server, with each tool earning its place across session creation, continuation, monitoring, cancellation, output retrieval, discovery, and teardown. Nothing seems redundant or filler.
The surface covers a full session lifecycle: create, reply, status/list, cancel, output paging, config/catalog discovery, and end/cleanup. Coverage is strong; only minor conveniences (e.g. a dedicated session-list beyond the status-without-id path) are absent, which agents can work around.