Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
ChimeraForge
MCP serversLocal-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance
chimeraforge@0.101.0 -
math-mcp
MCP serversGPU-accelerated MCP server: symbolic algebra, numerical computing, FFT, optimization, linear algebra
scicomp-math-mcp@0.1.6 -
BioHarbor
MCP serversRun real bioinformatics from your AI agent. Reliable, reproducible, on your own GPUs.
bioharbor@0.1.6 -
XportL
MCP serversGPU fabric tools: NCCL benchmark analysis, degradation cost, cluster compatibility, XportL facts.
-
VRAMGlass
MCP serversLive GPU prices, VRAM requirements and local LLM hardware planning from VRAMGlass.
-
Galactic
MCP serversOn-chain asset, market, and GPU price data for galactic.inc.
-
FastGPU
MCP serversCompare live GPU cloud rental prices and match workloads to the cheapest provider.
-
ComputeSage StackBench
MCP serversGPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
-
Entyrax
MCP serversPC hardware decision engine for Brazil (pt-BR): compatibility, GPU recommendations, build analysis.
-
MDEngine
MCP serversMD workbench for agents: 13 analysis tools, renders, hosted GPU runs; LAMMPS + OpenMM.
https://github.com/forcefieldsilicon/mdengine/releases/download/v0.7.1/mdengine-mcp-0.7.1-macos-arm64.mcpb -
offers
MCP serversLive VPS, bare metal and GPU hosting prices across ~75 providers, rescraped daily.
-
kilawatt-mcp-server
MCP serversKilawatt Cloud MCP server: request GPU compute with account or x402 payments.
kilawatt-mcp-server@0.3.0 -
Project Bourne
MCP serversRun reproducible scientific workloads on GPUs, local compute, Slurm, and PBS with provenance.
@project-bourne/mcp@0.6.0 -
molecular-mcp
MCP serversGPU-accelerated MCP server for molecular dynamics, N-body simulations, and particle systems
scicomp-molecular-mcp@0.1.6 -
neural-mcp
MCP serversGPU-accelerated MCP server for neural network training, deep learning, and model experimentation
scicomp-neural-mcp@0.1.6 -
dcp-mcp
MCP serversSaudi sovereign AI compute: OpenAI-compatible inference, rent GPU pods, manage storage.
-
capacity-attest
MCP serversSigned delivery claims for x402 capacity trades: GPU-hours, storage, API credits, bandwidth.
capacity-attest@0.7.0 -
OneInfer
MCP serversSigned-in OneInfer models, chat, media, Studio movies, music, GPUs, and credits.
-
rigshare
MCP serversRent GPUs, robots, drones, and construction gear on RIGShare; also onboards equipment owners.
rigshare-mcp@2.2.1 -
mcp
MCP serversRent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain.
@prismnetwork/mcp@0.8.4 -
Histopathology Annotation MCP
MCP serversImage annotation, incl. histopathology: nuclei, outlines, QC → QuPath/COCO/YOLO. No GPU.
label-image-mcp@0.9.0 -
ParalonCloud
MCP serversRent GPUs on ParalonCloud, or as a provider manage your nodes, prices and earnings.
@paraloncloud/mcp@1.5.0 -
project-maya
AI repositoriesProject Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
git clone https://github.com/mw00/project-maya.git -
llama-modchip
Agents & frameworksRun 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
git clone https://github.com/synchopate/llama-modchip.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.