Enables LangChain agents to access decentralized GPU compute tools for network status, cost estimation, distributed matrix multiplication, similarity search, and PCA/SVD.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
matrix-compute-mcp: Official MCP Server & High-Level Verifiable AI Primitives
matrix-compute-mcp is an independent extension package built on top of matrix-compute-sdk that provides:
High-Level Verifiable AI Primitives (matrix_compute_mcp.ai): Drop-in PyTorch layers (DistributedLinear, DistributedLoRALinear), massive exact cosine similarity search (distributed_cosine_similarity), and distributed spectral PCA/SVD (distributed_pca_svd) — all verified in $O(n^2)$ via Freivalds' algorithm.
Official Model Context Protocol Server (matrix-compute-mcp): Exposes decentralized GPU TFLOPS to autonomous AI agents (Claude Desktop, Cursor, Antigravity, LangChain, OpenClaw) over stdio/JSON-RPC 2.0 with L402 Macaroon or trial API key authentication.
{
"mcpServers": {
"matrix-compute": {
"command": "uvx",
"args": ["matrix-compute-mcp"],
"env": {
"MATRIX_NOSTR_RELAYS": "wss://relay.matrix-compute.net",
"MATRIX_SETTLEMENT_API_URL": "https://settlement.matrix-compute.net",
"MATRIX_L402_MACAROON": "<your-l402-macaroon-or-leave-unset-for-trial>"
}
}
}
}Tool Name | Description |
| Queries the discovery relay for live GPU worker count, total VRAM, TEE enclaves, and |
| Computes exact upload/download bandwidth (MB), task count, GFLOPs, and satoshi cost estimates via |
| Executes verified distributed matrix multiplication $C = A \times B$ from |
| Runs massive exact $K$-NN cosine similarity search using |
| Runs verified top-$k$ randomized SVD or stateful remote-VRAM power-iteration PCA/SVD. |
matrix_compute_mcp.ai)import numpy as np
from matrix_compute_mcp.ai import (
DistributedLinear,
DistributedLoRALinear,
distributed_cosine_similarity,
distributed_pca_svd,
)
# 1. Exact K-NN Cosine Similarity with OUTPUT_GRID_2D zero download redundancy
scores, indices = distributed_cosine_similarity(queries, corpus_embeddings, top_k=10)
# 2. Drop-in PyTorch Linear & LoRA Linear layers with verified forward & backward passes
layer = DistributedLinear(in_features=4096, out_features=4096)
lora_layer = DistributedLoRALinear(in_features=4096, out_features=4096, r=16, lora_alpha=32.0)
# 3. Distributed Randomized SVD / Stateful Power-Iteration PCA
U, S, Vt = distributed_pca_svd(embeddings, k=32, method="randomized")This server cannot be deployed
On-demand GPU nodes for agents: create nodes, run commands, and submit jobs, billed by the minute.
GPU compute for agents: run commands on an L4/A100/H100, watch logs, billed per second.
Rent cloud GPUs from AI agents: live prices, VRAM estimates, launch, logs and stop.
Discover verified AI inference nodes, get the best node+model per task, pre-price chains.
