now.roundtable.mcp/roundtable

Official13 tools

Roundtable

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

Multi-model AI debates with 200+ models that discuss and synthesize insights.

Captured live from the server via tools/list.

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.

Parameters (1)

thinking_levelstring
Filter to a specific thinking level

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.

Parameters (3)

limitinteger
Max results to return
offsetinteger
Pagination offset
tool_namestring
Filter by tool name (e.g., "consult", "architect")

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.

Parameters (1)

session_idstringrequired
The session ID to retrieve

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.

Parameters (7)

end_timenumber
End timestamp (ms) for time range filter
eventstring
Filter by event name (e.g., "debate_completed")
levelstring
Filter by log level
limitinteger
Max results
offsetinteger
Pagination offset
session_idstring
Filter logs for a specific session
start_timenumber
Start timestamp (ms) for time range filter

check-usage

Check your remaining credits, usage limits, and plan info

Parameters (1)

verboseboolean
Include detailed per-window rate limit breakdown

get-thread-link

Get the dashboard URL for a previous debate session. Returns the thread link and public URL if the thread is public.

Parameters (1)

session_idstringrequired
The session ID to get the thread link for

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.

Parameters (2)

is_publicbooleanrequired
Set to true to make the thread publicly accessible, false to make it private
session_idstringrequired
The session ID from a previous debate

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.

Parameters (11)

contextstring
Additional background context for the debate (code, docs, requirements)
formatstring
Moderator output format: discussion (narrative), adr (architecture decision), comparison (table), pros-cons
modestring
Conversation mode: analyzing (research), brainstorming (ideas), debating (tradeoffs), solving (action plans)
modelsarray
Override specific model IDs. Min 3 models. Use list-models to see available options
promptstringrequired
The question, topic, or problem to debate
rolesarray
Inline role names for participants (e.g., ["Security Architect", "Backend Engineer"])
thinking_levelstring
Controls model quality and cost: low (fast/cheap), medium (balanced), high (maximum reasoning)
webhook_urlstring
Webhook URL to POST results to after completion
session_contextarray
Session IDs to use as context (max 3). Prior moderator summaries will be prepended.
knowledgearray
Reference knowledge to inject as context
auto_routeboolean
Auto-select optimal models based on prompt analysis and historical performance

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.

Parameters (5)

descriptionstringrequired
What the system should do
focus_areasarray
Priority areas (e.g., ["security", "performance"])
scalestring
Target scale: startup (small team), growth (scaling), enterprise (large org)
tech_stackarray
Preferred technologies
webhook_urlstring
Webhook URL to POST results to after completion

review-code

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

Parameters (5)

codestringrequired
The code to review
focusarray
Review focus areas (e.g., ["security", "performance"])
languagestring
Programming language (auto-detected if not specified)
thinking_levelstring
Review depth: low (quick scan), medium (balanced), high (thorough)
webhook_urlstring
Webhook URL to POST results to after completion

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.

Parameters (8)

codebase_contextstring
Relevant existing code, file structure, or architecture notes
constraintsarray
Constraints (e.g., ["no breaking changes", "must support offline"])
featurestringrequired
The feature or change to plan
tech_stackarray
Current tech stack
thinking_levelstring
Planning depth
webhook_urlstring
Webhook URL to POST results to after completion
session_contextarray
Session IDs to use as context (max 3). Prior moderator summaries will be prepended.
knowledgearray
Reference knowledge to inject as context

debug-issue

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

Parameters (8)

codestring
The relevant code where the bug occurs
errorstring
Error message, stack trace, or unexpected output
expected_behaviorstring
What should happen vs what actually happens
problemstringrequired
Describe the bug, failure, or unexpected behavior
thinking_levelstring
Analysis depth
webhook_urlstring
Webhook URL to POST results to after completion
session_contextarray
Session IDs to use as context (max 3). Prior moderator summaries will be prepended.
knowledgearray
Reference knowledge to inject as context

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.

Parameters (7)

contextstring
Background context — codebase, team, timeline, constraints
decisionstringrequired
The decision or question to evaluate
optionsarray
Specific options to compare
prioritiesarray
What matters most (e.g., ["performance", "dx", "cost"])
thinking_levelstring
Analysis depth
webhook_urlstring
Webhook URL to POST results to after completion
session_contextarray
Session IDs to use as context (max 3). Prior moderator summaries will be prepended.

Install

claude_desktop_config.json

{
  "mcpServers": {
    "roundtable": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.roundtable.now/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.