Connect Roundtable and your agent gets 13 tools, among them assess-tradeoffs, check-usage, consult-council. It answers at https://mcp.roundtable.now/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 12 September 2026; the last check, on 24 October 2026, succeeded.
Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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. Inputs: context, decision, options, priorities, thinking_level, webhook_url |
check-usage | Check your remaining credits, usage limits, and plan info Inputs: verbose |
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 Inputs: context, format, mode, models, prompt, roles |
debug-issue | Debugging council. Root Cause Analyst, Systems Engineer, and Edge Case Investigator collaboratively diagnose bugs, analyze errors, and propose fixes. Inputs: code, error, expected_behavior, problem, thinking_level, webhook_url |
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. Inputs: description, focus_areas, scale, tech_stack, webhook_url |
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. Inputs: end_time, event, level, limit, offset, session_id |
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. Inputs: session_id |
get-thread-link | Get the dashboard URL for a previous debate session. Returns the thread link and public URL if the thread is public. Inputs: session_id |
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. Inputs: 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. Inputs: limit, offset, tool_name |
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. Inputs: codebase_context, constraints, feature, tech_stack, thinking_level, webhook_url |
review-code | Code review council. Senior Engineer, Security Reviewer, and Performance Analyst analyze your code and a moderator synthesizes their findings. Inputs: code, focus, language, thinking_level, webhook_url |
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. Inputs: is_public, session_id |
Every block below points at https://mcp.roundtable.now/mcp. Pick your client and copy.
claude mcp add --transport http roundtable https://mcp.roundtable.now/mcp
{
"mcpServers": {
"roundtable": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.roundtable.now/mcp"]
}
}
}{
"mcpServers": {
"roundtable": {
"url": "https://mcp.roundtable.now/mcp"
}
}
}{
"servers": {
"roundtable": {
"type": "http",
"url": "https://mcp.roundtable.now/mcp"
}
}
}{
"context_servers": {
"roundtable": {
"url": "https://mcp.roundtable.now/mcp"
}
}
}{
"mcpServers": {
"roundtable": {
"serverUrl": "https://mcp.roundtable.now/mcp"
}
}
}{
"mcpServers": {
"roundtable": {
"url": "https://mcp.roundtable.now/mcp"
}
}
}name: Roundtable
version: 0.0.1
schema: v1
mcpServers:
- name: Roundtable
type: streamable-http
url: https://mcp.roundtable.now/mcp{
"mcpServers": {
"roundtable": {
"httpUrl": "https://mcp.roundtable.now/mcp"
}
}
}{
"mcpServers": {
"roundtable": {
"type": "http",
"url": "https://mcp.roundtable.now/mcp"
}
}
}{
"mcpServers": {
"roundtable": {
"url": "https://mcp.roundtable.now/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.roundtable.now%2Fmcp&type=streamable_http&id=roundtable&name=Roundtable
It answered our last check on 24 October 2026 in 431 ms. Over 6 checks since 12 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by roundtable.now and served from mcp.roundtable.now, the vendor's own domain: https://mcp.roundtable.now/mcp.
13, as returned by the server's own tools/list on 23 September 2026: assess-tradeoffs, check-usage, consult-council, debug-issue, design-architecture, get-logs, get-session, get-thread-link, and 5 more.
It answered our last check on 24 October 2026 in 431 ms. Over 6 checks since 12 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.roundtable.now/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: now.roundtable.mcp. Endpoint host: mcp.roundtable.now. ARD identifier: urn:air:now.roundtable.mcp:mcp:roundtable.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.