MCP server for orchestrating OpenCode instances across machines via SSH reverse tunnels
Command line client for Bkper
DuckDuckGo web search tool for OpenCode with deep search capabilities
Agent kit (skills, agents, personas) for the Zenku ecosystem — works with Claude Code, OpenCode, and Codex CLI.
🔍 Blast radius & caller analysis for legacy Java. Heuristic-ranked impact audit — npm-installable agent skill for OpenCode, Codex, Claude Code, Copilot, Gemini & DeepCode.
Lightdash CLI tool
Deep research MCP server: multi-source search + CRAAP evaluation + cross-verification + professional reports
Stdio adapter for the hosted Instadash MCP server at https://mcp.instadash.io/. Use this only if your MCP client doesn't support remote OAuth servers.
Metarhia Skills
MCP server for time, calendar, timezone, Chinese lunar calendar, almanac, and date utilities
Repo-local memory v2 plugin for opencode
Unified MCP server manager for AI coding agents
MCP server for brand-name verification. Three tools — verify_brand_name (5-axis verdict on a single candidate), compare_brand_names (2-5 finalist comparison), get_naming_methodology (public methodology lookup) — route to the anonymous-first /v1/verify end
OpenCode plugin for Project Warcraft - from vibe coding to warcraft coding
MCP server for Garmin Connect - access fitness, health and training data
211 MCP tools across 76 developer APIs (192 VanMoose + Truncus, obqo, TenScore, WebIntel) — one server, one bring-your-own-key per service
一键安装qx-agw skill到各平台
Zuora MCP
MCP (Model Context Protocol) server for Composter - Let AI assistants access your React component vault
Opencode plugin to remind and auto-submit prompts when todos are open
MCP server for seamless AI agent session handoffs via local SQLite storage
Parse, normalize, and query AI coding agent transcripts — Claude Code JSONL sessions first, Codex and OpenCode additive. Local-only; never uploads.
MCP server for food image analysis and nutrition data via TastyAPI
The first AI teaching skill with dual-mode switching. Concise mode for quick review, detailed 7-step mode for systematic learning.