Roundtable

now.roundtable.mcpPublished by mcp.roundtable.nowOfficial publisherv1.0.2Updated Oct 27, 2026

Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Remote MCP server that runs multi-model AI "councils" — several models debate an engineering question and a moderator synthesizes the answer.

What you can do
  • Run a multi-model council on an engineering question, with automatic or manually chosen models and roles
  • Design architecture, review code, plan an implementation, debug an issue, or assess tradeoffs through specialized councils
  • List available models by thinking level, with credit costs and capabilities
  • Review past sessions: list them, fetch full results with participant responses and moderator synthesis, and get dashboard or public thread links
  • Set a thread public or private
  • Check remaining credits and plan limits, and query structured execution logs by session, severity, event type and time range
When to use it
Useful when you want a second, third and fourth opinion on engineering decisions — architecture, code review, debugging, planning or tradeoffs — rather than a single model's answer, and when you want those debates recorded and reviewable later.
Requirements
A remote endpoint at mcp.roundtable.now over streamable HTTP. Requires a Roundtable account and an API key sent in the X-API-Key header; the key is created in the Roundtable chat settings. Usage consumes credits tied to a plan.
Before you install
The API key is a secret sent as a header. Council runs consume credits, so check usage before heavy use. Prompts, code and questions are sent to Roundtable and to multiple third-party models. Setting a thread public makes it shareable by URL, so keep sensitive code or design details private.

Installation

In SourceWeft

  1. Open Roundtable in the dashboard and add it to a workspace.
  2. Connect X-API-Key credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/now.roundtable.mcp%2Froundtable/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "roundtable": {
      "type": "http",
      "url": "https://mcp.roundtable.now/mcp",
      "headers": {
        "X-API-Key": "<YOUR_API_KEY>"
      }
    }
  }
}

README

This repository has no README.

Tools

13

list-models

List Models

List available AI models grouped by thinking level (low/medium/high). Shows default models, credit costs, capabilities for each tier. Use this before consult to understand model options.

Parametersthinking_level

list-sessions

List Sessions

List your previous MCP tool sessions. Returns session metadata including prompt, tool used, quality score, and credits consumed. Useful for reviewing past council discussions.

Parameterslimitoffsettool_name

get-session

Get Session

Get full details of a previous MCP session by ID. Returns the complete result including participant responses and moderator synthesis. Use list-sessions first to find session IDs.

Parameterssession_idrequired

get-logs

Get Logs

Query structured logs from your MCP tool executions. Filter by session, severity level, event type, and time range. Useful for debugging and monitoring tool usage.

Parameterseventlevellimitoffsetend_timesession_idstart_time

check-usage

Check Usage

Check your remaining credits, usage limits, and plan info

Parametersverbose

set-thread-visibility

Set Thread Visibility

Set a thread as public or private. Public threads can be shared via URL. Use session_id from a previous debate session.

Parametersis_publicrequiredsession_idrequired

consult-council

Consult Council

Consult the AI coding council — multiple models discuss your engineering question sequentially (each sees prior responses), then a moderator synthesizes. Auto-mode by default — AI picks optimal models, roles, and conversation mode from your prompt. Provide explicit models to override (manual mode). Fully configurable: mode, format, roles, models, thinking level.

Parametersmoderolesformatmodelspromptrequiredcontextknowledgeauto_routewebhook_urlthinking_levelsession_context

design-architecture

Design Architecture

Architecture design council. Systems Architect, Infrastructure Engineer, and DX Advocate evaluate your system design. Always uses high thinking for maximum depth. Output as ADR.

Parametersscaletech_stackdescriptionrequiredfocus_areaswebhook_url

review-code

Review Code

Code review council. Senior Engineer, Security Reviewer, and Performance Analyst analyze your code and a moderator synthesizes their findings.

Parameterscoderequiredfocuslanguagewebhook_urlthinking_level

plan-implementation

Plan Implementation

Implementation planning council. Tech Lead, Senior Engineer, and QA Strategist break down a feature into actionable steps, identify risks, and define acceptance criteria. Output as ADR.

Parametersfeaturerequiredknowledgetech_stackconstraintswebhook_urlthinking_levelsession_contextcodebase_context

debug-issue

Debug Issue

Debugging council. Root Cause Analyst, Systems Engineer, and Edge Case Investigator collaboratively diagnose bugs, analyze errors, and propose fixes.

Parameterscodeerrorproblemrequiredknowledgewebhook_urlthinking_levelsession_contextexpected_behavior

assess-tradeoffs

Assess Tradeoffs

Tradeoff assessment council. Pragmatist, Skeptic, and Futurist evaluate options from different angles — short-term vs long-term, risk vs reward, simplicity vs flexibility. Output as pros-cons.

Parameterscontextoptionsdecisionrequiredprioritieswebhook_urlthinking_levelsession_context

Version history

1
  1. v1.0.2LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.