LLM Tools
Give any LLM access to micro-tools through MCP servers — each powered by a specialized AI generation pipeline for a domain language.
Overview
Every Graffiticode micro-tool is an MCP server. Any agent that speaks MCP can connect, describe what it wants, and get back a working result. Each micro-tool includes a specialized AI generation pipeline for its domain language, so the calling LLM never needs to know syntax or implementation details.
How It Works
- LLM specifies requirements - Natural language description of the desired outcome
- Vertical AI generates code - Domain-specific AI translates requirements to Graffiticode
- Compiler produces output - Code compiles to interactive components
- User interacts - Rendered UI collects data or displays information
The LLM doesn't need to know Graffiticode syntax. It simply describes what it needs, and the vertical AI handles the translation.
Tool Definitions
create_item
Create an interactive component from a natural language description.
| Parameter | Type | Description |
|---|---|---|
language | string | The language code (e.g., "L0152", "L0166") |
description | string | Natural language description of what to create |
name | string | Optional name for the item |
update_item
Modify an existing item with natural language instructions.
| Parameter | Type | Description |
|---|---|---|
item_id | string | The ID of the item to update |
modification | string | Natural language description of the changes to make |
get_item
Retrieve an item by its ID.
| Parameter | Type | Description |
|---|---|---|
item_id | string | The ID of the item to retrieve |
list_languages
Discover available languages and their capabilities.
| Parameter | Type | Description |
|---|---|---|
category | string | Optional category filter |
search | string | Optional search term |
get_language_info
Get detailed information about a specific language.
| Parameter | Type | Description |
|---|---|---|
language | string | The language code (e.g., "L0152") |
Dedicated AI Architecture
Each Graffiticode micro-tool has its own dedicated AI:
| Language | Domain | Vertical AI Capability |
|---|---|---|
| L0002 | Base Language | Core functionality shared across all languages |
| L0137 | Data Transformation | GraphQL queries, flattening, reshaping data |
| L0152 | Interactive Maps | Markers, layers, geospatial data visualization |
| L0159 | Flashcards | Learning cards, spaced repetition, memorization |
| L0166 | Spreadsheets | Formulas, cell formatting, spreadsheet assessments |
Benefits
- No syntax learning - LLMs describe intent, not implementation
- Domain expertise - Vertical AIs encode best practices for each domain
- Reliable output - Consistent, working code every time
- Iterative refinement - Use
update_itemto modify existing components