matrix-compute-mcp

by matrix-compute.com MCP server in GPU & serverless compute, indexed and not reviewed

HostedLocalvendor's own

Not reviewed

No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.

How the index works

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

What the official MCP registry says

Facts

MCP registry
com.matrix-compute/matrix-compute-mcp · 0.1.4
Endpoint
https://mcp.matrix-compute.net/mcp
Packages
pypi matrix-compute-mcp stdio
PyPI / week
414
GitHub stars
0
Registry entry
updated 15 Nov 2026

From the official MCP registry, the package registries and our own checks. JSON · Markdown

Why it's listed

  • It's published in the registry under matrix-compute.com, a namespace the registry only gives to whoever proves they control that domain.

Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.

Tools it lists 5 · about 1,305 tokens of context · checked 8 hours ago

ToolWhat it doesHint
get_network_statusQueries the Matrix Compute discovery relay for live GPU worker availability, total VRAM capacity, confidential computing (TEE) enclaves, and sats_per_gflop pricing.
estimate_job_costCalculates exact upload/download network bandwidth (MB), task count, GFLOPs, and satoshi cost estimates for a distributed matrix multiplication C (m x n) = A (m x k) x B (k x n).
execute_distributed_matmulExecutes verified distributed matrix multiplication C = A x B across decentralized GPU workers with dynamic Freivalds verification and L402 settlement. Accepts file paths (.npy, .npz, .safetensors) or inline 2D JSON…
batch_similarity_searchRuns exact cosine similarity search between query embeddings (M x D) and corpus embeddings (N x D) on distributed GPUs using OUTPUT_GRID_2D zero-reduction tiling.
compute_pca_svdComputes verified top-k Principal Component Analysis (PCA) / Singular Value Decomposition (SVD) on distributed GPU workers via randomized subspace iteration or stateful power iteration.

What https://mcp.matrix-compute.net/mcp answered to tools/list, asked without credentials. answered without the initialize handshake. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.

How its tools read to an agent 0 errors · 8 warnings · 1 note

  • warnTC12batch_similarity_searchno type for corpus_embeddings, queries
  • warnTC12compute_pca_svdno type for matrix
  • warnTC12execute_distributed_matmulno type for matrix_a, matrix_b
  • warnTC16batch_similarity_searchno readOnlyHint or destructiveHint
  • warnTC16compute_pca_svdno readOnlyHint or destructiveHint
  • warnTC16estimate_job_costno readOnlyHint or destructiveHint
  • warnTC16execute_distributed_matmulno readOnlyHint or destructiveHint
  • warnTC16get_network_statusno readOnlyHint or destructiveHint
  • noteTC24server5 of 5 tools have no outputSchema

The checks from /check and anchor check, run each day on the list above: about 1,305 tokens of definitions. Not part of the score yet. Check your own server.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.