Roundtable
Server Details
Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 13 tools
The tool set separates general consultation (consult-council) from specialized councils for tradeoffs, debugging, architecture, implementation planning, and code review. Session management and utility tools (logs, usage, models, sessions) are clearly distinct. Only minor potential overlap exists between consult-council and the specialized councils, but descriptions clarify the purpose of each.
All tools follow a consistent verb_noun pattern in snake_case (e.g., consult-council, get-session, list-models). Verbs are varied but predictable, and compound nouns are hyphenated consistently. No mixed conventions.
13 tools is appropriate for a platform that offers multiple council workflows plus session, log, and usage management. Each tool addresses a distinct need without unnecessary bloat.
The server covers the full lifecycle of a council-based workflow: model discovery (list-models), execution (consult-council and specialized councils), session retrieval (list-sessions, get-session), sharing (get-thread-link, set-thread-visibility), and operational support (check-usage, get-logs). Missing delete/update session tools are minor and not essential for the core purpose.
Available Tools
13 toolsassess-tradeoffsAssess TradeoffsAInspect
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.
Inputs: decision (required), context, options, priorities, +3 more.
check-usageCheck UsageARead-onlyIdempotentInspect
Check your remaining credits, usage limits, and plan info
Inputs: verbose. Returns: plan, status, credits, rateLimits
consult-councilConsult CouncilAInspect
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.
Inputs: prompt (required), mode, roles, format, +7 more.
debug-issueDebug IssueBInspect
Debugging council. Root Cause Analyst, Systems Engineer, and Edge Case Investigator collaboratively diagnose bugs, analyze errors, and propose fixes.
Inputs: problem (required), code, error, knowledge, +4 more.
design-architectureDesign ArchitectureBInspect
Architecture design council. Systems Architect, Infrastructure Engineer, and DX Advocate evaluate your system design. Always uses high thinking for maximum depth. Output as ADR.
Inputs: description (required), scale, tech_stack, focus_areas, +1 more.
get-logsGet LogsARead-onlyIdempotentInspect
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.
Inputs: event, level, limit, offset, +3 more. Returns: logs
get-sessionGet SessionARead-onlyIdempotentInspect
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.
Inputs: session_id (required). Returns: id, prompt, toolName, createdAt, +3 more
get-thread-linkGet Thread LinkARead-onlyIdempotentInspect
Get the dashboard URL for a previous debate session. Returns the thread link and public URL if the thread is public.
Inputs: session_id (required). Returns: isPublic, publicUrl, dashboardUrl
list-modelsList ModelsARead-onlyIdempotentInspect
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.
Inputs: thinking_level. Returns: levels
list-sessionsList SessionsARead-onlyIdempotentInspect
List your previous MCP tool sessions. Returns session metadata including prompt, tool used, quality score, and credits consumed. Useful for reviewing past council discussions.
Inputs: limit, offset, tool_name. Returns: hasMore, sessions
plan-implementationPlan ImplementationAInspect
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.
Inputs: feature (required), knowledge, tech_stack, constraints, +4 more.
review-codeReview CodeAInspect
Code review council. Senior Engineer, Security Reviewer, and Performance Analyst analyze your code and a moderator synthesizes their findings.
Inputs: code (required), focus, language, webhook_url, +1 more.
set-thread-visibilitySet Thread VisibilityAIdempotentInspect
Set a thread as public or private. Public threads can be shared via URL. Use session_id from a previous debate session.
Inputs: is_public (required), session_id (required). Returns: isPublic, publicUrl
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
One prompt. ~100 independent AI models. One report: consensus, disagreements, and minority insights.
Five AI models debate your decision blind, then give one recommendation and the strongest objection.
Multiple AIs peer-review and debate your question, then return one fact-checked answer.
Deliberation + live 5-model council divergence over the Omnarai multi-AI attributed corpus.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables multi-round brainstorming debates between multiple AI models like GPT, DeepSeek, and Ollama to produce synthesized final outputs. Users can orchestrate parallel model interactions where AI agents critique and refine each other's ideas to reach a consolidated conclusion.7111 npm73MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables Claude to orchestrate multi-model AI roundtable discussions between GPT-4o, Gemini, Grok, and DeepSeek through independent responses and cross-critique rounds. It supports various discussion presets such as debate, brainstorm, and consensus to facilitate diverse perspectives and synthesis.MIT
- FlicenseNot gradedqualityDmaintenanceOrchestrates sequential debates between multiple AI models across four phases (constructive, challenge, closing, synthesis) with host intervention and anti-sycophancy enforcement.-
- FlicenseNot gradedqualityCmaintenanceConvene a panel of expert AI personas to debate any topic, idea, or decision from every side. Runs the debate, cites live web sources, maps where the experts disagree, and returns a synthesized briefing.-
Glama MCP Gateway
Add one secure layer between your agents and this server.