Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SAPTIVA_API_KEYYesYour Saptiva API key, obtainable from Saptiva Lab (https://lab.saptiva.com/)

Tools

Functions exposed to the LLM to take actions

NameDescription
saptiva_chat

Send a chat completion request to Saptiva AI models. Supports multiple models including Saptiva Turbo (fast), Cortex (reasoning), Legacy (tool-compatible), and more.

saptiva_reason

Use Saptiva Cortex for complex reasoning tasks. Shows the model's chain-of-thought reasoning process along with the final answer. Best for math, logic, analysis, and multi-step problems.

saptiva_ocr

Extract text from images using Saptiva OCR model. Supports both URLs and base64 encoded images. Great for document processing, receipt scanning, and image text extraction.

saptiva_embed

Generate semantic embeddings for text using Saptiva Embed model. Useful for similarity search, clustering, and RAG applications.

saptiva_batch_embed

Generate embeddings for multiple texts at once. More efficient than calling saptiva_embed multiple times.

saptiva_list_models

List all available Saptiva AI models with their capabilities, descriptions, and pricing.

saptiva_help

🎓 GUÍA PARA PRINCIPIANTES - Muestra ejemplos de peticiones y respuestas de la API de Saptiva.

Temas disponibles:

  • quick_start: Inicio rápido con ejemplo básico

  • chat_example: Ejemplo completo de chat con request/response

  • reasoning_example: Ejemplo de razonamiento con Cortex

  • ocr_example: Ejemplo de extracción de texto de imágenes

  • embedding_example: Ejemplo de generación de embeddings

  • all_tools: Lista de todas las herramientas disponibles

  • curl_examples: Ejemplos en cURL para usar directamente

  • agents_sdk: Información sobre Saptiva Agents SDK para construir agentes

Prompts

Interactive templates invoked by user choice

NameDescription
code_reviewReview code for bugs, improvements, and best practices
explain_conceptExplain a technical concept in simple terms
write_documentationGenerate documentation for code or APIs
debug_helpHelp debug an error or issue
mexican_legalGet help with Mexican legal and regulatory context using Saptiva KAL

Resources

Contextual data attached and managed by the client

NameDescription
Saptiva ModelsList of available Saptiva AI models and their capabilities
Saptiva PricingPricing information for Saptiva models (per million tokens)

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LaraArias/MCP-Saptiva'

If you have feedback or need assistance with the MCP directory API, please join our Discord server