Roundtable
REMOTE · MCP.ROUNDTABLE.NOW · SCANNED SEP 20
Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.
Available components
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. How we score → Why this is hard to score →
Endpoint Security83
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- 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. See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability86
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- 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. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (54% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Roundtable MCP server?
Roundtable is a hosted endpoint at https://mcp.roundtable.now/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.roundtable.now
claude mcp add --transport http now-roundtable-mcp-roundtable 'https://mcp.roundtable.now/mcp'
{
"mcpServers": {
"now-roundtable-mcp-roundtable": {
"url": "https://mcp.roundtable.now/mcp"
}
}
} {
"servers": {
"now-roundtable-mcp-roundtable": {
"type": "http",
"url": "https://mcp.roundtable.now/mcp"
}
}
} [mcp_servers.now-roundtable-mcp-roundtable] url = "https://mcp.roundtable.now/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"now-roundtable-mcp-roundtable": {
"type": "remote",
"url": "https://mcp.roundtable.now/mcp",
"enabled": true
}
}
} openclaw mcp add now-roundtable-mcp-roundtable --url 'https://mcp.roundtable.now/mcp' --transport streamable-http
mcp_servers:
now-roundtable-mcp-roundtable:
url: "https://mcp.roundtable.now/mcp" {
"McpServers": {
"now-roundtable-mcp-roundtable": {
"Transport": "http",
"Url": "https://mcp.roundtable.now/mcp"
}
}
} assistant mcp add now-roundtable-mcp-roundtable -t streamable-http -u 'https://mcp.roundtable.now/mcp'
{
"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.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 26 Aug 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 0
- Stability: 0.97 → pass security
- 24 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 31 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 30 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Jul 26 0
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Probed https://mcp.roundtable.now/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=roundtable.now | CN=WE1,O=Google Trust Services,C=US | 30 Aug 2026 | 28 Nov 2026 | ECDSA 256 | ECDSA-SHA256 | 1184c76002c80d7a1325f460de4e32cb |
| SANs: roundtable.now, mcp.roundtable.now | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.roundtable.now. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| now. | present | 53572 | 8 | Verified |
| roundtable.now. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Challenged, unverified
The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.
| Result | Challenged, unverified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
Protected resource metadata
| Retrieved | No |
|---|---|
| Problem | no_resource_metadata |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.roundtable.now/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.roundtable.now/mcp | HTTPS enforced | 301 | https://mcp.roundtable.now/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
assess-tradeoffs Assess Tradeoffs ~168
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.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | Background context — codebase, team, timeline, constraints |
| decision | string | yes | 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 |
No output schema declared.
No examples provided.
check-usage Check Usage ~35
Check your remaining credits, usage limits, and plan info
| Name | Type | Req | Description |
|---|---|---|---|
| verbose | boolean | – | Include detailed per-window rate limit breakdown |
| Name | Type | Req | Description |
|---|---|---|---|
| credits | number | yes | Remaining credit balance |
| plan | string | yes | Current plan tier |
| rateLimits | object | yes | Rate limit status across all windows |
| status | string | yes | Overall usage status |
No examples provided.
consult-council Consult Council ~319
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | 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 |
No output schema declared.
No examples provided.
debug-issue Debug Issue ~162
Debugging council. Root Cause Analyst, Systems Engineer, and Edge Case Investigator collaboratively diagnose bugs, analyze errors, and propose fixes.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | 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 |
No output schema declared.
No examples provided.
design-architecture Design Architecture ~122
Architecture design council. Systems Architect, Infrastructure Engineer, and DX Advocate evaluate your system design. Always uses high thinking for maximum depth. Output as ADR.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | yes | 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 |
No output schema declared.
No examples provided.
get-logs Get Logs ~136
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 |
| Name | Type | Req | Description |
|---|---|---|---|
| logs | array | yes | Matching log entries |
No examples provided.
get-session Get Session ~53
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.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | The session ID to retrieve |
| Name | Type | Req | Description |
|---|---|---|---|
| createdAt | string | yes | Session creation timestamp |
| durationMs | – | yes | Duration in milliseconds |
| id | string | yes | Session identifier |
| prompt | string | yes | Original prompt text |
| qualityScore | – | yes | AI-rated quality score |
| toolName | string | yes | Tool that was invoked |
| totalCredits | – | yes | Total credits consumed |
No examples provided.
get-thread-link Get Thread Link ~49
Get the dashboard URL for a previous debate session. Returns the thread link and public URL if the thread is public.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | The session ID to get the thread link for |
| Name | Type | Req | Description |
|---|---|---|---|
| dashboardUrl | string | yes | Dashboard URL to view the thread |
| isPublic | boolean | yes | Whether the thread is publicly accessible |
| publicUrl | – | yes | Public share URL if thread is public |
No examples provided.
list-models List Models ~58
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.
| Name | Type | Req | Description |
|---|---|---|---|
| thinking_level | string | – | Filter to a specific thinking level |
| Name | Type | Req | Description |
|---|---|---|---|
| levels | array | yes | Available thinking level tiers |
No examples provided.
list-sessions List Sessions ~80
List your previous MCP tool sessions. Returns session metadata including prompt, tool used, quality score, and credits consumed. Useful for reviewing past council discussions.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results to return |
| offset | integer | – | Pagination offset |
| tool_name | string | – | Filter by tool name (e.g., "consult", "architect") |
| Name | Type | Req | Description |
|---|---|---|---|
| hasMore | boolean | yes | Whether more results are available |
| sessions | array | yes | List of sessions |
No examples provided.
plan-implementation Plan Implementation ~173
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.
| Name | Type | Req | Description |
|---|---|---|---|
| codebase_context | string | – | Relevant existing code, file structure, or architecture notes |
| constraints | array | – | Constraints (e.g., ["no breaking changes", "must support offline"]) |
| feature | string | yes | 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 |
No output schema declared.
No examples provided.
review-code Review Code ~119
Code review council. Senior Engineer, Security Reviewer, and Performance Analyst analyze your code and a moderator synthesizes their findings.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | 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 |
No output schema declared.
No examples provided.
set-thread-visibility Set Thread Visibility ~73
Set a thread as public or private. Public threads can be shared via URL. Use session_id from a previous debate session.
| Name | Type | Req | Description |
|---|---|---|---|
| is_public | boolean | yes | Set to true to make the thread publicly accessible, false to make it private |
| session_id | string | yes | The session ID from a previous debate |
| Name | Type | Req | Description |
|---|---|---|---|
| isPublic | boolean | yes | Current visibility state |
| publicUrl | – | yes | Public share URL if thread is public |
No examples provided.
What is the Roundtable MCP server?
Roundtable is an MCP server listed in the public MCP registry as now.roundtable.mcp/roundtable. Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight. This page covers its hosted endpoint (https://mcp.roundtable.now/mcp).
Is the Roundtable MCP server safe to use?
Roundtable scores 91 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Roundtable MCP server expose?
Roundtable exposes 13 tools: list-models, list-sessions, get-session, get-logs, check-usage, and 8 more. Their descriptions and schemas cost roughly 1,547 tokens of context every time the server is loaded.
Does the Roundtable MCP server require authentication?
Yes. Roundtable asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Roundtable MCP server still maintained?
Roundtable is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.