Dual Model MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENROUTER_API_KEY | Yes | Your OpenRouter API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| query_dual_modelsA | Schickt eine Prompt parallel an mehrere Modelle via OpenRouter (Standard: anthropic/claude-fable-5.1, openai/gpt-6-astra, Reasoning-Effort high). Eskalationsstufe für harte Probleme, nicht für Routinefragen: teuer und langsam. Liefert alle Antworten nebeneinander, optional mit Synthese (Konvergenzen, Widersprüche, Unikate). Standard-System-Prompt: strukturierte Antwort in 6-8 Absätzen. |
| ask_gptA | Holt eine Zweitmeinung von openai/gpt-5.6-sol (Reasoning-Effort high) via OpenRouter. Günstige Alltagsvariante für eine andere Perspektive, keine Eskalation. Das Modell sieht nur den Prompt: Kontext, Code und bisherige Versuche mitgeben. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have distinct purposes: query_dual_models is an escalation tool for hard problems with parallel multi-model synthesis, while ask_gpt is a cheap everyday second opinion. The descriptions explicitly differentiate them (e.g., 'keine Eskalation'), though both involve querying external models, so mild overlap remains.
Both names follow a verb_noun snake_case pattern (query_dual_models, ask_gpt). The verbs 'query' and 'ask' are synonyms rather than identical, and the nouns differ in specificity, but the convention is readable and consistent enough.
Two tools is slightly below the typical 3-15 range, but each tool serves a clear, distinct use case (escalation vs. everyday second opinion). The count is well-scoped for a focused dual-model query server.
The surface covers the two main workflows: multi-model escalation and single-model second opinion. Minor gaps exist, such as no tool to discover available models or configure model defaults, but core needs are met.