Skip to main content
Glama

Roundtable

Server Details

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

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

See and control every tool call

Log every tool call with full inputs and outputs
Control which tools are enabled per connector
Manage credentials once, use from any MCP client
Monitor uptime and get alerted when servers go down

Available Tools

13 tools
assess-tradeoffsInspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
contextNoBackground context — codebase, team, timeline, constraints
optionsNoSpecific options to compare
decisionYesThe decision or question to evaluate
prioritiesNoWhat matters most (e.g., ["performance", "dx", "cost"])
webhook_urlNoWebhook URL to POST results to after completion
thinking_levelNoAnalysis depthmedium
session_contextNoSession IDs to use as context (max 3). Prior moderator summaries will be prepended.
check-usageInspect

Check your remaining credits, usage limits, and plan info

ParametersJSON Schema
NameRequiredDescriptionDefault
verboseNoInclude detailed per-window rate limit breakdown
consult-councilInspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
modeNoConversation mode: analyzing (research), brainstorming (ideas), debating (tradeoffs), solving (action plans)debating
rolesNoInline role names for participants (e.g., ["Security Architect", "Backend Engineer"])
formatNoModerator output format: discussion (narrative), adr (architecture decision), comparison (table), pros-consdiscussion
modelsNoOverride specific model IDs. Min 3 models. Use list-models to see available options
promptYesThe question, topic, or problem to debate
contextNoAdditional background context for the debate (code, docs, requirements)
knowledgeNoReference knowledge to inject as context
auto_routeNoAuto-select optimal models based on prompt analysis and historical performance
webhook_urlNoWebhook URL to POST results to after completion
thinking_levelNoControls model quality and cost: low (fast/cheap), medium (balanced), high (maximum reasoning)medium
session_contextNoSession IDs to use as context (max 3). Prior moderator summaries will be prepended.
debug-issueInspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault
codeNoThe relevant code where the bug occurs
errorNoError message, stack trace, or unexpected output
problemYesDescribe the bug, failure, or unexpected behavior
knowledgeNoReference knowledge to inject as context
webhook_urlNoWebhook URL to POST results to after completion
thinking_levelNoAnalysis depthmedium
session_contextNoSession IDs to use as context (max 3). Prior moderator summaries will be prepended.
expected_behaviorNoWhat should happen vs what actually happens
design-architectureInspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault
scaleNoTarget scale: startup (small team), growth (scaling), enterprise (large org)startup
tech_stackNoPreferred technologies
descriptionYesWhat the system should do
focus_areasNoPriority areas (e.g., ["security", "performance"])
webhook_urlNoWebhook URL to POST results to after completion
get-logsInspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
eventNoFilter by event name (e.g., "debate_completed")
levelNoFilter by log level
limitNoMax results
offsetNoPagination offset
end_timeNoEnd timestamp (ms) for time range filter
session_idNoFilter logs for a specific session
start_timeNoStart timestamp (ms) for time range filter
get-sessionInspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
session_idYesThe session ID to retrieve
list-modelsInspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
thinking_levelNoFilter to a specific thinking level
list-sessionsInspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMax results to return
offsetNoPagination offset
tool_nameNoFilter by tool name (e.g., "consult", "architect")
plan-implementationInspect

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
featureYesThe feature or change to plan
knowledgeNoReference knowledge to inject as context
tech_stackNoCurrent tech stack
constraintsNoConstraints (e.g., ["no breaking changes", "must support offline"])
webhook_urlNoWebhook URL to POST results to after completion
thinking_levelNoPlanning depthmedium
session_contextNoSession IDs to use as context (max 3). Prior moderator summaries will be prepended.
codebase_contextNoRelevant existing code, file structure, or architecture notes
review-codeInspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault
codeYesThe code to review
focusNoReview focus areas (e.g., ["security", "performance"])
languageNoProgramming language (auto-detected if not specified)
webhook_urlNoWebhook URL to POST results to after completion
thinking_levelNoReview depth: low (quick scan), medium (balanced), high (thorough)medium
set-thread-visibilityInspect

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

ParametersJSON Schema
NameRequiredDescriptionDefault
is_publicYesSet to true to make the thread publicly accessible, false to make it private
session_idYesThe session ID from a previous debate

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.