com.matrix-compute/matrix-compute-mcp
PYPI · MATRIX-COMPUTE-MCP · 2 COMPONENTS
P2P GPU matrix multiply, exact cosine search, and PCA/SVD verified via Freivalds' algorithm.
Available components
Last scanned (10 hours ago)
Scores higher than 42% of PyPI servers
Category AI and Machine Learning
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. How we score → Why this is hard to score →
Supply Chain Security44
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- 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. View diagnostics → Partial
- 4 of 64 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 5 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability61
- AI-judged instruction clarity (good).Pass
- 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. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 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. See how to fix → Fail
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (14)
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (2)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 19 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 15 Nov 26 46
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed pypi/matrix-compute-mcp@0.1.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 2 scripts
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | setuptools.build_meta |
| setup_py | Not reviewed | <setup.py, unreviewed> |
Background: Why install scripts are a supply-chain risk →
Dependencies 64 packages
| Packages resolved | 64 |
|---|---|
| No linked repository | 4 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
batch_similarity_search ~162
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.
| Name | Type | Req | Description |
|---|---|---|---|
| corpus_embeddings | – | yes | 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 | – | yes | 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. |
No output schema declared.
No examples provided.
compute_pca_svd ~154
Computes verified top-k Principal Component Analysis (PCA) / Singular Value Decomposition (SVD) on distributed GPU workers via randomized subspace iteration or stateful power iteration.
| Name | Type | Req | Description |
|---|---|---|---|
| center | boolean | – | Mean-center columns before decomposition (standard PCA). |
| k | integer | yes | Number of top singular/principal components to extract. |
| matrix | – | yes | 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. |
No output schema declared.
No examples provided.
estimate_job_cost ~228
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).
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | Inner dimension K (columns of A / rows of B). |
| m | integer | yes | Rows of matrix A (M > 0). |
| n | integer | yes | 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. |
No output schema declared.
No examples provided.
execute_distributed_matmul ~251
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.
| Name | Type | Req | Description |
|---|---|---|---|
| dtype | string | – | Computation precision ('fp32', 'fp16', 'bf16'). |
| matrix_a | – | yes | File path (.npy/.npz/.safetensors) or inline 2D array for matrix A (M x K). |
| matrix_b | – | yes | 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. |
No output schema declared.
No examples provided.
get_network_status ~87
Queries the Matrix Compute discovery relay for live GPU worker availability, total VRAM capacity, confidential computing (TEE) enclaves, and sats_per_gflop pricing.
| Name | Type | Req | Description |
|---|---|---|---|
| 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). |
No output schema declared.
No examples provided.
How do I install the com.matrix-compute/matrix-compute-mcp server?
com.matrix-compute/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.
pypi · matrix-compute-mcp
claude mcp add com-matrix-compute-matrix-compute-mcp -- uvx matrix-compute-mcp
What is the com.matrix-compute/matrix-compute-mcp server?
com.matrix-compute/matrix-compute-mcp is listed in the public MCP registry as com.matrix-compute/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 com.matrix-compute/matrix-compute-mcp server safe to use?
com.matrix-compute/matrix-compute-mcp scores 46 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 com.matrix-compute/matrix-compute-mcp server expose?
com.matrix-compute/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 com.matrix-compute/matrix-compute-mcp server still maintained?
com.matrix-compute/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 com.matrix-compute/matrix-compute-mcp server under?
com.matrix-compute/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 com.matrix-compute/matrix-compute-mcp server?
VerifyMCP ran 14 checks on com.matrix-compute/matrix-compute-mcp, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about com.matrix-compute/matrix-compute-mcp: Malware scan and Stability. One category scores 0 for that reason, because we only credit what we can confirm. 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.