Back to Browse

Matrix Compute MCP Server

Developer ToolsUse Caution1.5MCP RegistryLocalRemote
Free

Server data from the Official MCP Registry

P2P GPU matrix multiply, exact cosine search, and PCA/SVD verified via Freivalds' algorithm.

About

P2P GPU matrix multiply, exact cosine search, and PCA/SVD verified via Freivalds' algorithm.

Remote endpoints: streamable-http: https://mcp.matrix-compute.net/mcp

Security Report

1.5
Use Caution1.5Critical Risk

The server has no authentication enforced on its tools, and in HTTP mode it binds 0.0.0.0 with a wildcard CORS policy, so any remote client can call tools that take file paths for reading and writing. Tool results are also hardcoded as freivalds_verified true and status verified, which overstates what was actually checked, and mock mode is on by default. The code shown does not contain exfiltration or obvious malicious patterns, but the unauthenticated file I/O exposure drives the score below 7.0. Supply chain analysis found 11 known vulnerabilities in dependencies (1 critical, 6 high severity). Package verification found 1 issue.

5 files analyzed · 20 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

File System Read

Reads files on your machine. Normal for tools that analyze or process local data.

File System Write

Writes or modifies files on your machine. Check that this is expected for the tool.

HTTP Network Access

Connects to external APIs or services over the internet.

network_websocket

Check that this permission is expected for this type of plugin.

env_vars

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

Nostr discovery relay WebSocket URL (default: wss://relay.matrix-compute.net)Optional

Environment variable: MATRIX_NOSTR_RELAYS

Lightning L402 settlement service URL (default: https://settlement.matrix-compute.net)Optional

Environment variable: MATRIX_SETTLEMENT_API_URL

Optional Nostr Wallet Connect (nostr+walletconnect://) URI for mainnet jobsRequired

Environment variable: MATRIX_NWC_URI

How to Install & Connect

Available as Local & Remote

This plugin can run on your machine or connect to a hosted endpoint. during install.

Documentation

View on GitHub

From the project's GitHub README.

matrix-compute-mcp: Official MCP Server & High-Level Verifiable AI Primitives

PyPI version Open In Colab

matrix-compute-mcp is an official Model Context Protocol (MCP) server and high-level AI primitives package built on top of matrix-compute-sdk that provides:

  1. 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.
  2. Official Model Context Protocol Server (matrix-compute-mcp): Exposes decentralized GPU TFLOPS to autonomous AI agents (Claude Desktop, Cursor, Windsurf, Antigravity, LangChain, OpenClaw) over stdio (uvx matrix-compute-mcp) or remote Streamable HTTP (https://mcp.matrix-compute.net/mcp) with L402 Macaroon, NWC (nostr+walletconnect://), or zero-drain trial sandbox support.

Quick Start

1A. Local stdio MCP Client Configuration (Claude Desktop / Cursor / Antigravity)

{
  "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"
      }
    }
  }
}

1B. Hosted Remote MCP Endpoint (Zero Install)

Point any Streamable HTTP MCP client directly to:

https://mcp.matrix-compute.net/mcp

2. Exposed MCP Tools

Tool NameDescription
get_network_statusQueries the discovery relay for live GPU worker count, total VRAM, TEE enclaves, and sats_per_gflop pricing.
estimate_job_costComputes exact upload/download bandwidth (MB), task count, GFLOPs, and satoshi cost estimates via BandwidthProfiler.
execute_distributed_matmulExecutes verified distributed matrix multiplication $C = A \times B$ from .npy, .npz, .safetensors, or inline tensors.
batch_similarity_searchRuns massive exact $K$-NN cosine similarity search using OUTPUT_GRID_2D zero-reduction tiling.
compute_pca_svdRuns verified top-$k$ randomized SVD or stateful remote-VRAM power-iteration PCA/SVD.

3. High-Level Verifiable AI Primitives (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")

Reviews

No reviews yet

Be the first to review this server!