Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
matrix-compute-mcp
MCP serversP2P GPU matrix multiply, exact cosine search, and PCA/SVD verified via Freivalds' algorithm.
matrix-compute-mcp@0.1.4 -
OLTechX
MCP serversSearch Bulgarian tech listings, real used prices per model, GPU FPS estimates and PC build checks.
-
GrabGPU
MCP serversCloud GPU prices with live stock from 22 providers. Find where to rent an H100 or B300 now.
-
titan
MCP serversGPU compute API: LLM inference (ornith-1.5) on RTX 4080, pay-per-credit in Bitcoin.
-
TechEnthus Hardware Data API
MCP serversAuthenticated GPU/CPU/PSU lookup; beta power-budget estimate. Coverage/freshness vary by source.
-
forge-mcp-server
MCP serversTurn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup.
@rightnow/forge-mcp-server@1.0.2 -
agiscorecard-web3-compute
MCP serversCompare GPU workload costs per accepted output, including setup, storage, egress and failed work.
-
vllm-ops-mcp
MCP serversRead-only ops/health MCP server for a local vLLM instance: health tiers, GPU/VRAM, service status.
vllm-ops-mcp@0.1.0 -
godot-mcp
MCP serversGodot MCP server - Godot 4.x engine control via TCP bridge, STL/GLB/OBJ import, GPU particles, an...
https://github.com/sandraschi/godot-mcp/releases/download/v0.5.0-beta.1/godot-mcp-v0.5.0-beta.1.mcpb -
FLOPS Index
MCP serversGPU rental reference prices (spot, on-demand, DePIN), key-free; every value carries a verify URL.
flopsindex-mcp@0.12.5 -
corpusAI Cloud Pricing
Public APIsCloud, GPU and LLM token prices for agents, free discovery tools and paid per-call data
-
aicharged.io
MCP servers214 tools for AI agents over one MCP endpoint: image, video, audio, 3D, data, storage, mail, GPUs.
-
Orbit used tech prices
MCP serversUsed prices for GPUs, CPUs, RAM, consoles, iPhones, MacBooks and more from live eBay listings.
-
RigBase
MCP serversMeasured local-LLM tok/s on home AI rigs. Search builds, can-it-run, best GPU; sourced + linked.
-
webgl-animation-skills
Skills3D motion / WebGL skills for Claude Code — Three.js, GLSL shaders, particle systems, GPU render troubleshooting, and AI video direction, off the core 2D/Lottie path.
git clone https://github.com/iart-ai/webgl-animation-skills.git -
TANDIU AI infrastructure data
MCP serversFree, no auth. Daily CN AI infra: LLM prices, index, trends, GPU, estimators, agents, PC, funding.
-
Developer Utilities & Validators (Tanod)
MCP serversCloud GPU prices per hour, plus developer helpers: hash, HMAC, JWT, IDs, JSON, cron, time zones.
-
LLM Configurator
MCP serversRead-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
-
agentic.no
MCP serversFind GPU sellers for AI inference by model, cheapest first; pay per call with x402 (USDC on Base).
-
compute.wick.pics
MCP serversLive GPU spot market: 1,700+ offers, 10 provider feeds. History, watches, limit orders, no fee
-
Compute Screener
MCP serversGPU cloud pricing (H100, H200, B200 per hour) and AI model API pricing per 1M tokens, with history.
-
rent.dev
MCP serversLinux sandboxes billed by the second from a prepaid balance, and GPU pods on your own RunPod key.
rentdev@0.1.1 -
matrix-compute-mcp
MCP serversP2P GPU matrix multiply, exact cosine search, and PCA/SVD verified via Freivalds' algorithm.
matrix-compute-mcp@0.1.3 -
janas
AI repositories37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
git clone https://github.com/prabanta-dev/janas.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.