Dúos
Server Details
Two AI perspectives and a cross-review. OAuth required; new consultations use your Dúos quota.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool maps to a distinct resource+action: quota check, query creation, history listing, and result retrieval. Descriptions go out of their way to disambiguate side effects (crear_consulta consumes quota and calls models; the other three explicitly do not) and to forbid misuse of crear_consulta as a connectivity check.
All names use the same duos_ prefix with a consistent Spanish verb_noun snake_case pattern (consultar_cuota, crear_consulta, listar_consultas, obtener_resultado). The different verbs (consultar/listar/obtener) map to genuinely different operations rather than arbitrary variation.
Four tools is tight but each is essential: quota introspection, creating a job, listing history, and fetching the result. Nothing redundant, nothing obviously missing for the stated scope.
The query lifecycle (create → poll result → list history → check quota) is fully covered, with idempotency and polling guidance. Minor gap: no way to cancel a pending job or delete history entries, which an agent may want when a query was created in error.
Available Tools
4 toolsduos_consultar_cuotaConsultar tu cuota de DúosARead-onlyIdempotentInspect
Devuelve el plan, las consultas disponibles y el presupuesto propio de IA. No genera respuestas ni consume consultas. No muestra otros clientes ni el gasto global.
Inputs: response_format. Returns: budget, credits
duos_crear_consultaComparar dos perspectivas con DúosAIdempotentInspect
Crea una consulta autenticada: dos análisis iniciales separados y una revisión cruzada de cada modelo. Envía el texto a proveedores de IA y puede consumir UNA consulta del plan y gasto de IA. Requiere intención del cliente; no usar como comprobación gratuita de conexión. Devuelve jobId/status para consultar el resultado con duos_obtener_resultado. Reutiliza el MISMO idempotency_key UUID si reintentas la MISMA pregunta; nunca cambies el mensaje con esa clave.
Inputs: message (required), idempotency_key (required), mode, locale, +2 more. Returns: jobId, status, requestId, pollAfterMs
duos_listar_consultasVer tu historial de consultasARead-onlyIdempotentInspect
Lista una página del historial propio de consultas. Requiere el permiso separado duos:history. No genera respuestas. Continúa con nextOffset cuando no sea null.
Inputs: limit, offset, response_format. Returns: nextOffset, consultations
duos_obtener_resultadoRecuperar el resultado de una consultaARead-onlyIdempotentInspect
Recupera únicamente un trabajo propio creado antes. No vuelve a llamar a modelos ni descuenta consultas. Si sigue pendiente, respeta pollAfterMs antes de volver a leer. Un error no es un resultado completo.
Inputs: job_id (required), response_format. Returns: error, jobId, result, status, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Code review by AI models from different companies, usually two. Shows where they agree and disagree.
Independent second opinion on any AI answer: inaccuracies, gaps, and a scored report card.
Compare AI perspectives with configurable Modes, estimate deliberations, and retrieve run receipts.
A second opinion for AI agents: one prompt across several live Gonka models + roles, one call.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables an AI assistant to ask other AI models for a second opinion, compare 2–4 answers side by side, search the web, and check usage balance through an API gateway.63 npmMIT
- AlicenseNot gradedqualityAmaintenanceLets your AI assistant consult assistants from other vendors under your own subscriptions, track costs, and cross-examine answers across models to surface disagreements and open points.3 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.