Roundtable
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@RoundtableShould we use Rust or Go for the new microservice?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
๐ช Roundtable
A council of frontier models โ for the decisions that matter.
One question โ many minds โ one decision.
Fan a question out to Grok, Codex/OpenAI, GLM, MiniMax, Claude, and Gemini in parallel, optionally deliberate to consensus with a chaired vote, and get back one decided answer โ from the command line or any MCP-capable coding harness.
curl -fsSL https://roundtable.sh/install.sh | bashWhy Roundtable?
Every model has a blind spot it can't see. Right before an irreversible call โ an architecture, a migration, a rewrite โ is exactly when one model's confident answer deserves a second (and third, and fourth) opinion.
Roundtable convenes a panel of frontier models. Each answers independently; then, for
high-stakes calls, a multi-round deliberation lets every head read the whole table and
revise until a Claude chair declares CONSENSUS or names the remaining disagreement.
Disagreement is signal, not noise.
๐ณ๏ธ Advisory (default) โ every head answers once, blind to the others. Raw, independent reads.
โ๏ธ Deliberation (
--rounds N) โ heads see each other and revise; a neutral chair rulesCONSENSUS/CONTINUEand stops early on agreement.๐ API keys are enough โ no local CLIs required. Missing heads are skipped; the council runs on whatever subset you've configured.
๐ฆ One binary, everywhere โ a CLI, an MCP server, and a one-command installer that wires itself into your coding harness.
Related MCP server: MergeLoop
Example
$ roundtable "Reply with exactly: OK three words" --heads claude,gemini
# ๐ช Round Table โ 2 heads โ advisory
## ๐ต Claude (claude-opus-4-8, Anthropic) โ OK three words
## โจ Gemini (gemini-3.1-pro-preview, Google) โ OK three wordsAdd --rounds 3 and the heads deliberate; a chair prints VERDICT: CONSENSUS (or
CONTINUE) with the points they agreed on and any dissent named.
Install
curl -fsSL https://roundtable.sh/install.sh | bashOr pick your package manager โ all four deliver the same engine:
pip install roundtable
uv tool install roundtable
brew install frontier-infra/tap/roundtableThe installer places the engine under ${XDG_DATA_HOME:-~/.local/share}/roundtable,
symlinks roundtable into ~/.local/bin, and prints a PATH hint if needed.
Quickstart
# 1. Configure keys (masked prompts; shows which heads are โ/โ). Stored chmod-600
# in ~/.config/roundtable/config.env. Any subset works โ missing heads are skipped.
roundtable auth
# 2. Ask the council
roundtable "Postgres or SQLite for a single-tenant internal tool?"
# 3. Deliberate to consensus on a high-stakes call
roundtable ask -q "Should we rewrite the billing service in Go?" --rounds 3roundtable doctor shows which heads are configured and pings each for reachability.
Flags
-q/--question ยท -c/--context <file> (shared background for every head) ยท
--heads grok,codex,openai,glm,minimax,claude,gemini ยท --rounds N (deliberation) ยท
--research (web on, multi-step) ยท --timeout <secs> ยท --out <file>.
Exit 0 if at least one head answered.
The heads
Head | Provider | Key / auth |
๐ค Grok | xAI |
|
๐ง Codex | OpenAI | local |
๐ง OpenAI | OpenAI |
|
๐ฃ GLM | Z.AI |
|
๐ MiniMax | MiniMax |
|
๐ต Claude | Anthropic |
|
โจ Gemini |
|
Heads with no key/CLI are skipped inline โ the council runs on whatever subset you've configured, so API keys alone are enough (no local CLIs required).
MCP + wire into your harness
Roundtable ships an MCP server as a subcommand of the one binary:
roundtable mcp serve # stdio JSON-RPC; one tool: roundtable(question, heads?, rounds?, research?)
roundtable mcp config # prints the server JSON block to paste manuallyAuto-wire detected harnesses (idempotent โ backs up first, never clobbers):
roundtable install # detect + wire everything present
roundtable install --harness cursor,codex
roundtable install --all # non-interactiveWires Claude Code (skill + MCP), Cursor (~/.cursor/mcp.json),
Codex CLI (~/.codex/config.toml), and prints a generic JSON block for anything else:
{ "command": "roundtable", "args": ["mcp", "serve"] }Use in Claude Code
Roundtable ships as a Claude Code plugin โ a roundtable skill that drives the CLI.
Two ways to add it:
A โ Plugin marketplace (inside Claude Code):
/plugin marketplace add frontier-infra/roundtable
/plugin install roundtable@roundtableThe skill calls the globally-installed roundtable CLI, so install that first:
curl -fsSL https://roundtable.sh/install.sh | bash.
B โ roundtable install โ auto-wires the skill and the MCP server into Claude
Code (plus Cursor / Codex) in one step:
roundtable installCommands
roundtable "question" shorthand for `ask`
roundtable ask run the council (all engine flags)
roundtable auth [provider] configure API keys (masked, chmod-600)
roundtable models per-head model picker
roundtable heads enable/disable heads
roundtable doctor which heads are configured + reachability ping
roundtable config show / edit config.env
roundtable mcp serve|config MCP stdio server / print config
roundtable install auto-wire detected harnesses
roundtable version | update show version / upgrade in placeFor agents
Building on top of Roundtable? See AGENTS.md โ a concise guide for an
AI agent to install, configure, run, and wire Roundtable into its own harness.
Links
Website & docs โ https://roundtable.sh
Source โ https://github.com/frontier-infra/roundtable
Frontier Infra โ https://frontierinfra.org
License
MIT ยฉ Frontier Infra
This server cannot be deployed
Maintenance
Related MCP Connectors
Ask GPT, Claude, Gemini and Grok at once: one consensus answer plus where they agree and split.
Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
Commission a multi-model AI spec committee from your agent; get rubric-scored, build-ready specs.
Related MCP Servers
- AlicenseAqualityAmaintenanceEnables one AI coding agent to delegate tasks to, and build consensus across, multiple other coding CLIs (Claude Code, Codex, etc.) by orchestrating them as headless subprocesses.187MIT

MergeLoopofficial
AlicenseAqualityCmaintenanceA host-agnostic model council that routes tasks across multiple AI workers (MCP, CLI, API) and returns one unified answer.13Apache 2.0- FlicenseAqualityBmaintenanceA local stdio MCP server for running single-turn prompts across multiple model providers (OpenAI, Ollama, OpenRouter), allowing agents to fan out the same prompt to several models and combine the output.2-
- AlicenseNot gradedqualityAmaintenanceEnables orchestrating a panel of frontier AI models that independently propose, critique, revise, and converge on a single agreed answer to a problem, using existing vendor subscriptions or API keys.360 npm1MIT