About Prompt Switchboard MCP Sidecar
Prompt Switchboard MCP Sidecar is a Chrome side panel for comparing responses from multiple AI services with one prompt. It is intended for browser-based AI workflows and also serves as an MCP server for downstream agents.
Key features
- 01Host multiple AI services in one panel
- 02Send one prompt to multiple agents
- 03Compare answers side by side
- 04Hot-swap and fork conversations
Use cases
- 01Compare AI responses to a shared prompt
- 02Use multiple AI services without switching tabs
- 03Let downstream agents access the MCP bridge
MCP support
MultiAiPanel doubles as an MCP server for downstream agents. The README does not detail the MCP tools or resources it exposes.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README
MultiAiPanel
five AIs in one sidebar, one conversation, one ⌘+K
What You Get • Install • How It Work • Ecosystem
MultiAiPanel is a Chrome side panel that hosts every major AI side-by-side. One prompt, every model, side-by-side answers, no tab juggling.
┌──────────────────────────────────────┐
│ LOCAL-FIRST ████████ 100% │
│ SOURCE-TRACEABLE ████████ 100% │
│ TYPING REQUIRED ░░░░░░░░ 0% │
│ VIBES ████████ ZERO │
│ FILLER│
└──────────────────────────────────────┘
ChatGPT, Claude, Gemini, Grok, DeepSeek — same panel, same prompt, instant compare.
What You Get
| Surface | What |
|---|---|
sidepanel | All your AIs in one Chrome panel. Hot-swap, compare, fork. |
⌘+K compare mode | Send the same prompt to N agents. See answers next to each other. |
mcp bridge | MultiAiPanel doubles as an MCP server for downstream agents. |
public skills | Drop into Claude/Codex/OpenClaw. Spawn the gang on demand. |
Important
Local-first by default. No silent telemetry. No cloud round-trip. Your data stays on your machine until you explicitly ship it somewhere.
Install
git clone https://github.com/xiaojiou176-open/multi-ai-panel.git
cd MultiAiPanel
# follow the per-stack quickstart in INSTALL.md or docs/
Three commands. No curl | sh. No login. Read what you run.
Install break? Open your favorite agent and say "Read AGENTS.md and bootstrap MultiAiPanel for me." Agent fix own brain. Long version: docs/.
How It Work
The repo is seven layers — exactly the seven commits in git log. New work goes in as small named PRs. No 50-file mystery commits.
| Layer | What |
|---|---|
chore: scaffold | License, governance, hygiene gates, CI scaffolding. |
feat(core) | The primary engine. The reason MultiAiPanel exists. |
feat(modules) | Packages, adapters, services, plugins. The second floor. |
feat(contracts) | Schemas, configs, public boundaries. Other code talks here. |
test: | Receipts. Everything in this layer must run. |
feat(ops) | Scripts, infra, CI helpers, build glue. |
docs: | Public docs surface. The pretty face. |
git log reads like a building floor plan. Look once, know the whole shape.
Ecosystem
MultiAiPanel lives in the *Me family: three personal tools. command-style names, stupid-simple jobs.
| Repo | What |
|---|---|
| BeamMe | beam your agent config to any planet |
| BrewMe | wake up, news already brewed |
| MultiAiPanel (you here) | five AIs in one sidebar |
Cross-family taste: BeamMe · BrewMe · OpenVibeCoding · proofyard.
Star This Repo
If MultiAiPanel saves you a click, an hour, or a headache — star costs zero. Fair trade. ⭐
Also by Yifeng[Terry] Yu
- BeamMe — beam your agent config to any planet
- BrewMe — wake up, news already brewed
- OpenVibeCoding — AI codes overnight, you ship in the morning
- proofyard — every claim ships with its receipt
- dealyard — let prices fight, you sit and watch
License
MIT — small print, big freedom.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.