BlockRun MCPofficial
A
licenseA
qualityB
maintenanceProvides Claude with real-time access to markets, research, X/Twitter, and crypto data via a unified pay-per-call system with no API keys.
Last updated
20
1,059
478
MIT
Best NVIDIA MCP Servers
NVIDIA is a technology company that specializes in designing graphics processing units (GPUs) for gaming, professional visualization, data centers, and artificial intelligence applications. They are known for their cutting-edge hardware and software solutions that power everything from gaming PCs to supercomputers and AI systems.
Why this server?
Provides access to free-tier NVIDIA LLMs via the blockrun_chat tool.
Why this server?
Provides query expansion for semantic search using NVIDIA NIM API to generate hypothetical 3GPP-style answers, bridging vocabulary gap between queries and documents.
AlicenseBqualityFmaintenanceEnables AI assistants to search and retrieve information from 3GPP specification documents, including full-text search and specific lookup for LTE and 5G NAS cause values. It comes with pre-processed data for major specifications covering NAS, RRC, and protocol conformance testing.Last updated1435MITWhy this server?
Enables management of NVIDIA GPU-powered computing resources through RunPod's platform
RunPod MCP Serverofficial
AlicenseAqualityBmaintenanceEnables interaction with the RunPod REST API through Claude or other MCP-compatible clients, providing tools for managing pods, endpoints, templates, network volumes, and container registry authentications.Last updated504,51274Apache 2.0Why this server?
Used in examples for analyzing earnings call transcripts, particularly regarding AI chip demand statements from their CEO.
mcp-octagonofficial
AlicenseBqualityBmaintenanceDeliver real-time investment research with extensive private and public market data.Last updated3461142MITWhy this server?
Enables querying real-time trade data, valuation ratios, stock ratings, and price drivers for NVIDIA (NVDA.US) stock.
Infoway MCP Serverofficial
AlicenseAqualityDmaintenanceGives AI assistants access to real-time financial data including stock prices, crypto, forex, market sentiment, sector analysis, and company fundamentals via the Infoway API.Last updated17MITWhy this server?
Allows querying network configuration and state from NVIDIA Cumulus Linux switches via the NVUE API, providing read-only tools for platform, system, interfaces, VRFs, BGP, and more.
AlicenseBqualityCmaintenanceMCP server that integrates with the Cumulus Linux OS via NVUE API to read network configuration, interfaces, bridges, VRFs, BGP, and other network information.Last updated18MITWhy this server?
Allows assignment of NVIDIA GPUs (T4, L4, A100) to Colab runtimes via the change_runtime tool.
AlicenseAqualityAmaintenanceEnhanced fork of Google's Colab MCP, pre-registers all 7 notebook tools at startup (get_cells, add/run/update/delete/move_cell, add_text_cell), adds programmatic GPU control (T4/L4/A100) via OAuth, and fixes the "Disconnected from local server" issue with IPv4-only bind, PNA CORS headers, and stale-tab dedup. Works on Chrome, Edge, Windows, macOS, Linux.Last updated913Apache 2.0Why this server?
Provides tools to trace CUDA Runtime and Driver API calls, monitor kernel launches from libraries like cuBLAS and cuDNN, and diagnose GPU stalls and synchronization issues.
AlicenseAqualityBmaintenanceeBPF-based GPU causal observability agent with MCP server. Traces CUDA Runtime and Driver APIs via kernel uprobes and host events via tracepoints to build causal chains explaining GPU latency. 7 tools: get_check, get_trace_stats, get_causal_chains, get_stacks, run_demo, get_test_report, run_sql. Telegraphic compression reduces token usage ~60%. Supports stdio and HTTPS (TLS 1.3) transport.Last updated1184Why this server?
Utilizes NVIDIA's embedding API (nvidia/nv-embedqa-e5-v5) to create high-dimensional vector embeddings for accurate semantic search across memories.
AlicenseAqualityAmaintenanceDual-memory MCP system with PostgreSQL 17 + pgvector + NVIDIA NIM embeddings. 11 tools: search, save, profile, health, auto-repair, stats, tune, dedup, checkpoint, maintenance. Sparse Selective Caching (SSC) with 4-phase progressive retrieval. Bilingual EN/ES.Last updated113MIT