ArchitectGBT MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ARCHITECTGBT_API_KEY | No | Your API key for unlimited access (starts with agbt_) | |
| ARCHITECTGBT_API_URL | No | Custom API endpoint (default: https://architectgbt.com) |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_ai_recommendationA | Get AI model recommendations for SOFTWARE PROJECTS ONLY (web apps, APIs, chatbots, AI features, etc.). DO NOT use for physical projects, crafts, or non-software tasks. Analyzes requirements and recommends the best AI model with pricing, reasoning, and alternatives. Free tier: 3 recommendations/day. Add ARCHITECTGBT_API_KEY for unlimited access. |
| get_code_templateA | Get ArchitectGBT's production-tested code templates for AI model integration (TypeScript & Python). These are battle-tested templates with proper error handling, type safety, and best practices - NOT generic code. Pro feature - requires API key. Free users: browse models unlimited, get 3 AI recommendations/day. |
| list_modelsB | List available AI models with optional filtering by provider or capability. |
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 3 tools
Each tool has a clearly distinct responsibility: listing models, getting a recommendation, and fetching a code template. Descriptions are explicit about boundaries, especially the warning on get_ai_recommendation to not use it for non-software tasks.
All tool names follow a consistent verb_noun pattern in lowercase snake_case: get_ai_recommendation, get_code_template, list_models. No mixed conventions or vague verbs.
Three tools is within the typical well-scoped range and perfectly sized for a server that offers two core actions (recommend and template) plus a discovery/list function. Each tool earns its place.
The surface covers the full workflow for AI model integration: discover models (list_models), get a tailored recommendation (get_ai_recommendation), and obtain integration code (get_code_template). There are no obvious dead ends for the domain.