# Roundtable (remote · mcp.roundtable.now)

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

- Trust score: 78/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.roundtable.now`: 78/100 (this document), [markdown](https://verifymcp.io/servers/now-roundtable-mcp-roundtable/mcp.md), [page](https://verifymcp.io/servers/now-roundtable-mcp-roundtable/mcp)

## Channel facts

- Endpoint: `https://mcp.roundtable.now/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1810 tokens (~113/item across 16 items; 13 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (54% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http now-roundtable-mcp-roundtable https://mcp.roundtable.now/mcp
```

### Codex

```toml
[mcp_servers.now-roundtable-mcp-roundtable]
url = "https://mcp.roundtable.now/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "now-roundtable-mcp-roundtable": {
      "type": "remote",
      "url": "https://mcp.roundtable.now/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add now-roundtable-mcp-roundtable --url https://mcp.roundtable.now/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  now-roundtable-mcp-roundtable:
    url: "https://mcp.roundtable.now/mcp"
```

### Other

```json
{
  "mcpServers": {
    "now-roundtable-mcp-roundtable": {
      "type": "http",
      "url": "https://mcp.roundtable.now/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 77, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 74, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 72, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 71)

First indexed and scored.

## MCP tools (13)

### `list-models` (~58 tokens)

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.

Input parameters:

- `thinking_level` (string): Filter to a specific thinking level

Output parameters:

- `levels` (array): Available thinking level tiers

### `list-sessions` (~80 tokens)

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.

Input parameters:

- `limit` (integer): Max results to return
- `offset` (integer): Pagination offset
- `tool_name` (string): Filter by tool name (e.g., "consult", "architect")

Output parameters:

- `hasMore` (boolean): Whether more results are available
- `sessions` (array): List of sessions

### `get-session` (~53 tokens)

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.

Input parameters:

- `session_id` (string, required): The session ID to retrieve

Output parameters:

- `createdAt` (string): Session creation timestamp
- `durationMs`: Duration in milliseconds
- `id` (string): Session identifier
- `prompt` (string): Original prompt text
- `qualityScore`: AI-rated quality score
- `toolName` (string): Tool that was invoked
- `totalCredits`: Total credits consumed

### `get-logs` (~136 tokens)

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.

Input parameters:

- `end_time` (number): End timestamp (ms) for time range filter
- `event` (string): Filter by event name (e.g., "debate_completed")
- `level` (string): Filter by log level
- `limit` (integer): Max results
- `offset` (integer): Pagination offset
- `session_id` (string): Filter logs for a specific session
- `start_time` (number): Start timestamp (ms) for time range filter

Output parameters:

- `logs` (array): Matching log entries

### `check-usage` (~35 tokens)

Check Usage

Check your remaining credits, usage limits, and plan info

Input parameters:

- `verbose` (boolean): Include detailed per-window rate limit breakdown

Output parameters:

- `credits` (number): Remaining credit balance
- `plan` (string): Current plan tier
- `rateLimits` (object): Rate limit status across all windows
- `status` (string): Overall usage status

### `get-thread-link` (~49 tokens)

Get Thread Link

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

Input parameters:

- `session_id` (string, required): The session ID to get the thread link for

Output parameters:

- `dashboardUrl` (string): Dashboard URL to view the thread
- `isPublic` (boolean): Whether the thread is publicly accessible
- `publicUrl`: Public share URL if thread is public

### `set-thread-visibility` (~73 tokens)

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.

Input parameters:

- `is_public` (boolean, required): Set to true to make the thread publicly accessible, false to make it private
- `session_id` (string, required): The session ID from a previous debate

Output parameters:

- `isPublic` (boolean): Current visibility state
- `publicUrl`: Public share URL if thread is public

### `consult-council` (~319 tokens)

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.

Input parameters:

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

### `design-architecture` (~122 tokens)

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.

Input parameters:

- `description` (string, required): What the system should do
- `focus_areas` (array): Priority areas (e.g., ["security", "performance"])
- `scale` (string): Target scale: startup (small team), growth (scaling), enterprise (large org)
- `tech_stack` (array): Preferred technologies
- `webhook_url` (string): Webhook URL to POST results to after completion

### `review-code` (~119 tokens)

Review Code

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

Input parameters:

- `code` (string, required): The code to review
- `focus` (array): Review focus areas (e.g., ["security", "performance"])
- `language` (string): Programming language (auto-detected if not specified)
- `thinking_level` (string): Review depth: low (quick scan), medium (balanced), high (thorough)
- `webhook_url` (string): Webhook URL to POST results to after completion

### `plan-implementation` (~173 tokens)

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.

Input parameters:

- `codebase_context` (string): Relevant existing code, file structure, or architecture notes
- `constraints` (array): Constraints (e.g., ["no breaking changes", "must support offline"])
- `feature` (string, required): The feature or change to plan
- `knowledge` (array): Reference knowledge to inject as context
- `session_context` (array): Session IDs to use as context (max 3). Prior moderator summaries will be prepended.
- `tech_stack` (array): Current tech stack
- `thinking_level` (string): Planning depth
- `webhook_url` (string): Webhook URL to POST results to after completion

### `debug-issue` (~162 tokens)

Debug Issue

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

Input parameters:

- `code` (string): The relevant code where the bug occurs
- `error` (string): Error message, stack trace, or unexpected output
- `expected_behavior` (string): What should happen vs what actually happens
- `knowledge` (array): Reference knowledge to inject as context
- `problem` (string, required): Describe the bug, failure, or unexpected behavior
- `session_context` (array): Session IDs to use as context (max 3). Prior moderator summaries will be prepended.
- `thinking_level` (string): Analysis depth
- `webhook_url` (string): Webhook URL to POST results to after completion

### `assess-tradeoffs` (~168 tokens)

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.

Input parameters:

- `context` (string): Background context — codebase, team, timeline, constraints
- `decision` (string, required): The decision or question to evaluate
- `options` (array): Specific options to compare
- `priorities` (array): What matters most (e.g., ["performance", "dx", "cost"])
- `session_context` (array): Session IDs to use as context (max 3). Prior moderator summaries will be prepended.
- `thinking_level` (string): Analysis depth
- `webhook_url` (string): Webhook URL to POST results to after completion

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/now-roundtable-mcp-roundtable/mcp#diagnostics

## Score history

- 2026-08-03: 78
- 2026-08-02: 78
- 2026-08-01: 77
- 2026-07-31: 77
- 2026-07-30: 74
- 2026-07-29: 73
- 2026-07-28: 72
- 2026-07-27: 72
- 2026-07-26: 71

## Links

- Remote endpoint: https://mcp.roundtable.now/mcp
- Authorisation metadata: https://mcp.roundtable.now/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/deadpixel/roundtable-dashboard
- Changelog RSS feed: https://verifymcp.io/servers/now-roundtable-mcp-roundtable/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/now-roundtable-mcp-roundtable/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/now-roundtable-mcp-roundtable/mcp