MCP Hub
Back to servers

MCP-Saptiva

A comprehensive MCP server providing access to Saptiva AI's LLMs for chat, chain-of-thought reasoning, OCR, and semantic embeddings.

Tools
7
Updated
Jan 15, 2026

MCP-Saptiva

An MCP (Model Context Protocol) server for interacting with Saptiva AI's LLMs and tools.

Features

  • Chat Completions: Access Saptiva's various LLM models
  • Reasoning: Chain-of-thought reasoning with Saptiva Cortex
  • OCR: Extract text from images using Saptiva OCR
  • Embeddings: Generate semantic embeddings for text
  • Help System: Built-in documentation and examples

Available Tools

ToolDescription
saptiva_chatSend chat completion requests to Saptiva AI models
saptiva_reasonComplex reasoning with chain-of-thought (Cortex model)
saptiva_ocrExtract text from images using vision model
saptiva_embedGenerate semantic embeddings for text
saptiva_batch_embedBatch embedding generation for multiple texts
saptiva_list_modelsList all available models with pricing
saptiva_helpBuilt-in documentation and examples

Help Topics

Use saptiva_help with these topics:

TopicDescription
quick_startGetting started with Saptiva API
chat_exampleComplete chat request/response example
reasoning_exampleUsing Cortex for reasoning
ocr_exampleExtracting text from images
embedding_exampleGenerating embeddings
all_toolsList of all available tools
curl_examplescURL commands for terminal
agents_sdkSaptiva Agents SDK documentation

Available Prompts

PromptDescription
code_reviewReview code for bugs and improvements
explain_conceptExplain technical concepts at different levels
write_documentationGenerate documentation for code
debug_helpHelp debug errors and issues
mexican_legalMexican legal/regulatory questions (uses KAL model)

Available Models

ModelBest ForTools SupportPricing (per M tokens)
Saptiva TurboFast responses, high concurrencyYes$0.20 / $0.60
Saptiva CortexReasoning tasks with chain-of-thoughtYes$0.30 / $0.80
Saptiva OpsComplex cases, RAG, web searchNo$0.20 / $0.60
Saptiva LegacyCompatibility with legacy toolsYes$0.20 / $0.60
Saptiva OCRDocument text extraction, visionNo$0.15 / $0.50
Saptiva EmbedSemantic vectorizationN/A$0.01 / -
Saptiva KALMexico-specific contextYes$0.20 / $0.60

Installation

npm install
npm run build

Configuration

  1. Copy .env.example to .env:

    cp .env.example .env
    
  2. Add your Saptiva API key to .env:

    SAPTIVA_API_KEY=your_api_key_here
    
  3. Get your API key from Saptiva Lab

Usage with Claude Desktop

Add to your Claude Desktop MCP configuration:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "saptiva": {
      "command": "node",
      "args": ["/path/to/MCP-Saptiva/dist/index.js"],
      "env": {
        "SAPTIVA_API_KEY": "your_api_key_here"
      }
    }
  }
}

Quick Examples

Chat

{
  "model": "Saptiva Turbo",
  "messages": [
    {"role": "user", "content": "¿Qué es Python?"}
  ]
}

Reasoning

{
  "question": "Si tengo 5 manzanas y como 2, ¿cuántas quedan?",
  "max_tokens": 500
}

OCR

{
  "image_url": "https://example.com/document.png",
  "prompt": "Extrae todo el texto de esta imagen"
}

Embeddings

{
  "text": "Texto para convertir a vector"
}

Resources

The server exposes two resources:

  • saptiva://models - List of all models with capabilities
  • saptiva://pricing - Pricing information for all models

Development

# Install dependencies
npm install

# Build
npm run build

# Run tests
node test-comprehensive.mjs

Related Projects

Links

License

MIT

Reviews

No reviews yet

Sign in to write a review