A
licenseA
qualityC
maintenanceBridges any MCP client (like Claude Code, Zed, VS Code) to any ACP coding agent, enabling multi-agent orchestration from a single chat interface.
24
175 npm
12
Apache 2.0
OzBridge
by sena-labs
Related Servers
Alternatives to OzBridge
No user-submitted related servers found.
Related Servers
- AlicenseAqualityAmaintenanceBridges multiple CLI coding agents (Codex, Cursor, OpenCode, Claude, Antigravity) into any MCP client, enabling delegation of prompts, parallel execution, and code review workflows.60Mozilla Public 2.0
- AlicenseNot gradedqualityCmaintenanceCodeMCP — a secure, workspace-bound bridge between your machine and ChatGPT, Claude, or any AI agent.3MIT
- FlicenseNot gradedqualityAmaintenanceBridges MCP-capable AI coding agents and CLI users to their running VSCode instances for real-time language-server data. It enables fast diagnostics, symbol definition/hover/signature lookups, reference search, workspace-wide renames, and file opening without waiting on slow tsc or eslint runs.-
- MIT
- AlicenseNot gradedqualityAmaintenanceConnects MCP clients such as Claude, Cursor, and VS Code to OpenCode's headless API so they can delegate coding work across projects — asking questions, implementing features, launching and monitoring background jobs, responding to permission and input requests, and reviewing the resulting changes. It supports multi-project directories, configurable default provider/model pairs, and both synchronous and asynchronous task workflows.17,427 npmMIT
TDQS
A4.4/5.0
Scored across 6 tools
Disambiguation5/5
Each tool has a distinct purpose: local vs cloud execution, listing models, fetching run status, listing runs, setting default model. No ambiguity between tools.
Naming Consistency5/5
All tools use consistent snake_case naming with 'oz_' prefix and clear verb_noun pattern (e.g., oz_agent_run, oz_list_models, oz_run_get).
Tool Count5/5
6 tools cover the core workflow of running AI agents (local/cloud, model discovery, status polling, configuration) without being too many or too few.
Completeness4/5
Covers all essential operations: run locally, run in cloud, list models, check status, list runs, set default. Lacks a cancel/abort for cloud runs, which is a minor gap.
Maintenance
ActivityMaintained
ResponsivenessSlow