com.matrix-compute/matrix-compute-mcp
v0.1.4P2P GPU matrix multiply, exact cosine search, and PCA/SVD verified via Freivalds' algorithm.
Endpoint health
online- Last checked
- 11/20/2026, 9:16:59 AM
- Latency
- 40 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:com.matrix-compute%2Fmatrix-compute-mcp
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"com.matrix-compute/matrix-compute-mcp": {
"url": "https://mcp.matrix-compute.net/mcp"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
5 shown · authentication unknown
batch_similarity_search
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.
Schema valid · SHA-256 861d0b1ce9a4…
View input schema
{ "type": "object", "properties": { "queries": { "description": "File path (.npy/.npz/.safetensors) or inline 2D array of shape (M, D)." }, "corpus_embeddings": { "description": "File path (.npy/.npz/.safetensors) or inline 2D array of shape (N, D)." }, "top_k": { "type": "integer", "default": 5, "description": "Number of top matching corpus indices and scores to return per query." }, "dtype": { "type": "string", "enum": [ "fp32", "fp16", "bf16" ], "default": "fp32", "description": "Target GEMM precision." }, "output_path": { "type": "string", "description": "Optional file path (.npy/.safetensors) to save the full similarity matrix." } }, "required": [ "queries", "corpus_embeddings" ], "additionalProperties": false }compute_pca_svd
Computes verified top-k Principal Component Analysis (PCA) / Singular Value Decomposition (SVD) on distributed GPU workers via randomized subspace iteration or stateful power iteration.
Schema valid · SHA-256 e685a65a7278…
View input schema
{ "type": "object", "properties": { "matrix": { "description": "File path (.npy/.npz/.safetensors) or inline 2D array of shape (M, N)." }, "k": { "type": "integer", "description": "Number of top singular/principal components to extract." }, "center": { "type": "boolean", "default": true, "description": "Mean-center columns before decomposition (standard PCA)." }, "method": { "type": "string", "enum": [ "randomized", "power_iteration" ], "default": "randomized", "description": "Decomposition algorithm ('randomized' or 'power_iteration')." }, "output_path": { "type": "string", "description": "Optional output file path (.npz or .safetensors) to save U, S, Vt." } }, "required": [ "matrix", "k" ], "additionalProperties": false }
Connections
streamable-http
https://mcp.matrix-compute.net/mcp