Summary
You know those moments when you're stuck on a problem and wish you could get perspectives from multiple AI models at once? That's what this does. It orchestrates debates between GPT-4o, Claude, Gemini, and apparently 200+ other models, then synthesizes their responses into a single insight. Think of it as programmatic access to multi-model consensus building. You'd reach for this when you want to compare how different models approach the same prompt, validate reasoning across architectures, or just get a more robust answer by letting AIs argue it out first. It's accessed through streamable HTTP, so integration should be straightforward.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Tools
Public tool metadata for what this MCP can expose to an agent.
13 tools
list-modelsList 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.1 params
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* required
thinking_levelstringFilter to a specific thinking levelone of
low · medium · highlist-sessionsList your previous MCP tool sessions. Returns session metadata including prompt, tool used, quality score, and credits consumed. Useful for reviewing past council discussions.3 params
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* required
limitintegerMax results to returndefault: 20
offsetintegerPagination offsetdefault: 0
tool_namestringFilter by tool name (e.g., "consult", "architect")
get-sessionGet 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.1 params
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* required
session_idstringThe session ID to retrieve
get-logsQuery structured logs from your MCP tool executions. Filter by session, severity level, event type, and time range. Useful for debugging and monitoring tool usage.7 params
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* required
end_timenumberEnd timestamp (ms) for time range filter
eventstringFilter by event name (e.g., "debate_completed")
levelstringFilter by log levelone of
info · warn · errorlimitintegerMax resultsdefault: 50
offsetintegerPagination offsetdefault: 0
session_idstringFilter logs for a specific session
start_timenumberStart timestamp (ms) for time range filter
check-usageCheck your remaining credits, usage limits, and plan info1 params
Check your remaining credits, usage limits, and plan info
Parameters* required
verbosebooleanInclude detailed per-window rate limit breakdowndefault: false
get-thread-linkGet the dashboard URL for a previous debate session. Returns the thread link and public URL if the thread is public.1 params
Get the dashboard URL for a previous debate session. Returns the thread link and public URL if the thread is public.
Parameters* required
session_idstringThe session ID to get the thread link for
set-thread-visibilitySet a thread as public or private. Public threads can be shared via URL. Use session_id from a previous debate session.2 params
Set a thread as public or private. Public threads can be shared via URL. Use session_id from a previous debate session.
Parameters* required
is_publicbooleanSet to true to make the thread publicly accessible, false to make it private
session_idstringThe session ID from a previous debate
consult-councilConsult 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 o...11 params
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 o...
Parameters* required
auto_routebooleanAuto-select optimal models based on prompt analysis and historical performancedefault: false
contextstringAdditional background context for the debate (code, docs, requirements)
formatstringModerator output format: discussion (narrative), adr (architecture decision), comparison (table), pros-consone of
discussion · adr · comparison · pros-consdefault: discussionknowledgearrayReference knowledge to inject as context
modestringConversation mode: analyzing (research), brainstorming (ideas), debating (tradeoffs), solving (action plans)one of
analyzing · brainstorming · debating · solvingdefault: debatingmodelsarrayOverride specific model IDs. Min 3 models. Use list-models to see available options
promptstringThe question, topic, or problem to debate
rolesarrayInline role names for participants (e.g., ["Security Architect", "Backend Engineer"])
session_contextarraySession IDs to use as context (max 3). Prior moderator summaries will be prepended.
thinking_levelstringControls model quality and cost: low (fast/cheap), medium (balanced), high (maximum reasoning)one of
low · medium · highdefault: mediumwebhook_urlstringWebhook URL to POST results to after completion
design-architectureArchitecture design council. Systems Architect, Infrastructure Engineer, and DX Advocate evaluate your system design. Always uses high thinking for maximum depth. Output as ADR.5 params
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* required
descriptionstringWhat the system should do
focus_areasarrayPriority areas (e.g., ["security", "performance"])
scalestringTarget scale: startup (small team), growth (scaling), enterprise (large org)one of
startup · growth · enterprisedefault: startuptech_stackarrayPreferred technologies
webhook_urlstringWebhook URL to POST results to after completion
review-codeCode review council. Senior Engineer, Security Reviewer, and Performance Analyst analyze your code and a moderator synthesizes their findings.5 params
Code review council. Senior Engineer, Security Reviewer, and Performance Analyst analyze your code and a moderator synthesizes their findings.
Parameters* required
codestringThe code to review
focusarrayReview focus areas (e.g., ["security", "performance"])
languagestringProgramming language (auto-detected if not specified)
thinking_levelstringReview depth: low (quick scan), medium (balanced), high (thorough)one of
low · medium · highdefault: mediumwebhook_urlstringWebhook URL to POST results to after completion
plan-implementationImplementation 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.8 params
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* required
codebase_contextstringRelevant existing code, file structure, or architecture notes
constraintsarrayConstraints (e.g., ["no breaking changes", "must support offline"])
featurestringThe feature or change to plan
knowledgearrayReference knowledge to inject as context
session_contextarraySession IDs to use as context (max 3). Prior moderator summaries will be prepended.
tech_stackarrayCurrent tech stack
thinking_levelstringPlanning depthone of
low · medium · highdefault: mediumwebhook_urlstringWebhook URL to POST results to after completion
debug-issueDebugging council. Root Cause Analyst, Systems Engineer, and Edge Case Investigator collaboratively diagnose bugs, analyze errors, and propose fixes.8 params
Debugging council. Root Cause Analyst, Systems Engineer, and Edge Case Investigator collaboratively diagnose bugs, analyze errors, and propose fixes.
Parameters* required
codestringThe relevant code where the bug occurs
errorstringError message, stack trace, or unexpected output
expected_behaviorstringWhat should happen vs what actually happens
knowledgearrayReference knowledge to inject as context
problemstringDescribe the bug, failure, or unexpected behavior
session_contextarraySession IDs to use as context (max 3). Prior moderator summaries will be prepended.
thinking_levelstringAnalysis depthone of
low · medium · highdefault: mediumwebhook_urlstringWebhook URL to POST results to after completion
assess-tradeoffsTradeoff 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.7 params
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* required
contextstringBackground context — codebase, team, timeline, constraints
decisionstringThe decision or question to evaluate
optionsarraySpecific options to compare
prioritiesarrayWhat matters most (e.g., ["performance", "dx", "cost"])
session_contextarraySession IDs to use as context (max 3). Prior moderator summaries will be prepended.
thinking_levelstringAnalysis depthone of
low · medium · highdefault: mediumwebhook_urlstringWebhook URL to POST results to after completion
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Categories
Registryactive
TransportHTTP
AuthRequired
UpdatedMar 10, 2026
