# dev.pages.matrix-compute-website/matrix-compute-mcp (pypi · matrix-compute-mcp)

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

- Trust score: 64/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.matrix-compute.net`: 61/100, [markdown](https://verifymcp.io/servers/dev-pages-matrix-compute-website-matrix-compute-mcp/mcp.md), [page](https://verifymcp.io/servers/dev-pages-matrix-compute-website-matrix-compute-mcp/mcp)
- pypi · `matrix-compute-mcp`: 64/100 (this document), [markdown](https://verifymcp.io/servers/dev-pages-matrix-compute-website-matrix-compute-mcp/matrix-compute-mcp.md), [page](https://verifymcp.io/servers/dev-pages-matrix-compute-website-matrix-compute-mcp/matrix-compute-mcp)

## Channel facts

- Registry: `pypi`
- Package: `matrix-compute-mcp`
- Version: `0.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 94/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Declares code that runs automatically (setup.py) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does.
  - 4 of 64 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 882 tokens (~176/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_distributed_matmul" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the dev.pages.matrix-compute-website/matrix-compute-mcp server?

dev.pages.matrix-compute-website/matrix-compute-mcp runs locally as a PyPI package, launched with uvx matrix-compute-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add dev-pages-matrix-compute-website-matrix-compute- -- uvx matrix-compute-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "dev-pages-matrix-compute-website-matrix-compute-": {
      "command": "uvx",
      "args": [
        "matrix-compute-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-pages-matrix-compute-website-matrix-compute-": {
      "command": "uvx",
      "args": [
        "matrix-compute-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add dev-pages-matrix-compute-website-matrix-compute- -- uvx matrix-compute-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-pages-matrix-compute-website-matrix-compute-": {
      "type": "local",
      "command": [
        "uvx",
        "matrix-compute-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-pages-matrix-compute-website-matrix-compute- --command uvx --arg matrix-compute-mcp
```

### Hermes

```yaml
mcp_servers:
  dev-pages-matrix-compute-website-matrix-compute-:
    command: "uvx"
    args: ["matrix-compute-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "dev-pages-matrix-compute-website-matrix-compute-": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "matrix-compute-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-pages-matrix-compute-website-matrix-compute- -t stdio -c uvx -a matrix-compute-mcp
```

### Other

```json
{
  "mcpServers": {
    "dev-pages-matrix-compute-website-matrix-compute-": {
      "command": "uvx",
      "args": [
        "matrix-compute-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 64, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-19 (score 48, +2)

- [functional improvement] Stability: unverified → 0.13

### 2026-11-18 (score 46, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-17 (score 61, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-15 (score 46)

First indexed and scored.

## MCP tools (5)

### `get_network_status` (~87 tokens)

Queries the Matrix Compute discovery relay for live GPU worker availability, total VRAM capacity, confidential computing (TEE) enclaves, and sats_per_gflop pricing.

Input parameters:

- `max_price_per_gflop` (number): Maximum worker price filter in satoshis per GFLOP (optional).
- `min_vram_mb` (integer): Minimum worker VRAM filter in MB (optional).

### `estimate_job_cost` (~228 tokens)

Calculates 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).

Input parameters:

- `dtype` (string): Precision format ('fp32', 'fp16', 'bf16').
- `grid_cols` (integer): Column partitions P_c when using output_grid_2d.
- `grid_rows` (integer): Row partitions P_r when using output_grid_2d.
- `k` (integer, required): Inner dimension K (columns of A / rows of B).
- `m` (integer, required): Rows of matrix A (M > 0).
- `n` (integer, required): Columns of matrix B (N > 0).
- `num_strips` (integer): Strip count when using outer_product_1d.
- `partitioning_strategy` (string): Matrix partitioning strategy.
- `sats_per_gflop` (number): Override worker price in satoshis per GFLOP.
- `tile_size` (integer): Tile block size dimension.

### `execute_distributed_matmul` (~251 tokens)

Executes 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 arrays.

Input parameters:

- `dtype` (string): Computation precision ('fp32', 'fp16', 'bf16').
- `matrix_a` (required): File path (.npy/.npz/.safetensors) or inline 2D array for matrix A (M x K).
- `matrix_b` (required): File path (.npy/.npz/.safetensors) or inline 2D array for matrix B (K x N).
- `output_path` (string): Optional output file path (.npy, .npz, or .safetensors) to write C.
- `partitioning_strategy` (string): Matrix partitioning topology.
- `tensor_key_a` (string): Optional tensor key when loading matrix_a from .safetensors or .npz.
- `tensor_key_b` (string): Optional tensor key when loading matrix_b from .safetensors or .npz.
- `tile_size` (integer): Optional tile block size override.

### `batch_similarity_search` (~162 tokens)

Runs 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.

Input parameters:

- `corpus_embeddings` (required): File path (.npy/.npz/.safetensors) or inline 2D array of shape (N, D).
- `dtype` (string): Target GEMM precision.
- `output_path` (string): Optional file path (.npy/.safetensors) to save the full similarity matrix.
- `queries` (required): File path (.npy/.npz/.safetensors) or inline 2D array of shape (M, D).
- `top_k` (integer): Number of top matching corpus indices and scores to return per query.

### `compute_pca_svd` (~154 tokens)

Computes verified top-k Principal Component Analysis (PCA) / Singular Value Decomposition (SVD) on distributed GPU workers via randomized subspace iteration or stateful power iteration.

Input parameters:

- `center` (boolean): Mean-center columns before decomposition (standard PCA).
- `k` (integer, required): Number of top singular/principal components to extract.
- `matrix` (required): File path (.npy/.npz/.safetensors) or inline 2D array of shape (M, N).
- `method` (string): Decomposition algorithm ('randomized' or 'power_iteration').
- `output_path` (string): Optional output file path (.npz or .safetensors) to save U, S, Vt.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/dev-pages-matrix-compute-website-matrix-compute-mcp/matrix-compute-mcp#diagnostics

## Score history

- 2026-11-21: 64
- 2026-11-20: 64
- 2026-11-19: 48
- 2026-11-18: 46
- 2026-11-17: 61
- 2026-11-16: 46
- 2026-11-15: 46

## Common questions

### What is the dev.pages.matrix-compute-website/matrix-compute-mcp server?

dev.pages.matrix-compute-website/matrix-compute-mcp is listed in the public MCP registry as dev.pages.matrix-compute-website/matrix-compute-mcp. P2P GPU matrix multiply, exact cosine search, and PCA/SVD verified via Freivalds' algorithm. This page covers its PyPI package (matrix-compute-mcp).

### Is the dev.pages.matrix-compute-website/matrix-compute-mcp server safe to use?

dev.pages.matrix-compute-website/matrix-compute-mcp scores 64 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the dev.pages.matrix-compute-website/matrix-compute-mcp server expose?

dev.pages.matrix-compute-website/matrix-compute-mcp exposes 5 tools: get_network_status, estimate_job_cost, execute_distributed_matmul, batch_similarity_search, compute_pca_svd. Their descriptions and schemas cost roughly 882 tokens of context every time the server is loaded.

### Is the dev.pages.matrix-compute-website/matrix-compute-mcp server still maintained?

dev.pages.matrix-compute-website/matrix-compute-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the dev.pages.matrix-compute-website/matrix-compute-mcp server under?

dev.pages.matrix-compute-website/matrix-compute-mcp declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the dev.pages.matrix-compute-website/matrix-compute-mcp server?

VerifyMCP ran 16 checks on dev.pages.matrix-compute-website/matrix-compute-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/matrix-compute-mcp/
- Socket report: https://socket.dev/pypi/package/matrix-compute-mcp
- Repository: https://github.com/matrixmultiplyconsortium/matrix-compute-mcp
- Changelog RSS feed: https://verifymcp.io/servers/dev-pages-matrix-compute-website-matrix-compute-mcp/matrix-compute-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-pages-matrix-compute-website-matrix-compute-mcp/matrix-compute-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dev-pages-matrix-compute-website-matrix-compute-mcp/matrix-compute-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dev-pages-matrix-compute-website-matrix-compute-mcp/matrix-compute-mcp
