MCP For Claude Marketplace
SambaNova (AI Inference)

SambaNova (AI Inference) MCP Connector for Claude

A+

High-speed AI inference for Llama 3, DeepSeek, and MiniMax models via SambaNova's ultra-fast SN40L chips.

3 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect to SambaNova Cloud to run the world's fastest open-source models directly from your AI agent. Leverage the power of SambaNova's DataScale and SN40L infrastructure to achieve record-breaking tokens-per-second.

What you can do

  • Chat Completions — Generate high-quality responses using state-of-the-art models like Meta-Llama-3.3-70B-Instruct and DeepSeek-V3.1.
  • Agentic Responses — Use the specialized create_response tool for stateless, typed outputs designed specifically for agentic workflows.
  • Vector Embeddings — Generate high-dimensional text representations for RAG (Retrieval-Augmented Generation) using E5-Mistral-7B-Instruct.
  • Advanced Sampling — Fine-tune outputs with temperature, top_p, top_k, and seed parameters for deterministic and creative results.

How it works

  1. Subscribe to this server
  2. Enter your SambaNova Cloud API Key
  3. Start querying high-performance models from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Engineers — building real-time applications that require low-latency inference and high throughput.
  • Developers — looking for a cost-effective and faster alternative to standard LLM providers.
  • Data Scientists — generating embeddings for large-scale knowledge bases at scale.
llm-inferencellama3deepseekembeddingshigh-performance-computing

3 tools expose this connector's capabilities to your AI agent.

create_chat_completion

Compatible with OpenAI Chat Completions API. Create a chat completion using SambaNova models

create_embedding

Available on SambaStack. Create embeddings using SambaNova

create_response

Returns typed output items. Create a response using SambaNova Responses API

See how to talk to your AI agent using SambaNova (AI Inference).

Use create_chat_completion with Meta-Llama-3.3-70B-Instruct to explain how SN40L chips work.

I'll generate that explanation for you using Llama 3.3 on SambaNova. [The model explains the Reconfigurable Dataflow Architecture of SN40L...]

Generate an embedding for the sentence 'SambaNova is the fastest inference platform' using E5-Mistral-7B-Instruct.

I've generated the embedding vector for your text. It contains 4096 dimensions (example) ready for your vector database.

Use create_response with MiniMax-M2.7 to process this conversation history.

Processing the agentic workflow with MiniMax... I've returned the structured response items based on the input history provided.

You can use `create_chat_completion` with models like Meta-Llama-3.3-70B-Instruct, DeepSeek-V3.1, and MiniMax-M2.5 for high-speed text generation.

Related Connectors

TP

Traefik Proxy MCP

18 tools Official

Monitor and manage your Traefik Proxy infrastructure — inspect routers, services, and middlewares directly from your AI agent.

A+ View details →
SP

Spotio MCP

12 tools Official

Manage leads, pipelines, and field sales activities on Spotio with AI agents.

A+ View details →
NA

NOAA Aviation — Airport Weather Intelligence MCP

5 tools Official

Aviation weather data worldwide: METARs (current airport conditions), TAFs (24-hour airport forecasts), PIREPs (pilot reports of turbulence and icing), and SIGMETs/AIRMETs (significant aviation hazards) from the Aviation Weather Center.

A+ View details →
BP

Bright Pattern MCP

10 tools Official

Orchestrate your contact center via Bright Pattern — manage users, track interactions, and monitor real-time stats directly from any AI agent.

A+ View details →