Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.Filip-Pajalic/tensorcad

NPM · @TENSOR-CAD/MCP · SCANNED SEP 29

Design transformer LLM architectures and report their parameters, FLOPs, memory and cost

Available components

86 Trust /100
Trust breakdown (7 categories)

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 5 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to Filip-Pajalic/TensorCAD). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 2 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability87
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 5641 tokens (~74/item across 76 items; 19 tools + 57 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management20
  • Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage97
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 89% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 19 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the io.github.Filip-Pajalic/tensorcad MCP server?

io.github.Filip-Pajalic/tensorcad runs locally as an npm package, launched with npx -y @tensor-cad/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @tensor-cad/mcp

# add to Claude Code
claude mcp add filip-pajalic-tensorcad -- npx -y @tensor-cad/mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "filip-pajalic-tensorcad": {
      "command": "npx",
      "args": [
        "-y",
        "@tensor-cad/mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "filip-pajalic-tensorcad": {
      "command": "npx",
      "args": [
        "-y",
        "@tensor-cad/mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add filip-pajalic-tensorcad -- npx -y @tensor-cad/mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "filip-pajalic-tensorcad": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@tensor-cad/mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add filip-pajalic-tensorcad --command npx --arg -y --arg @tensor-cad/mcp
# ~/.hermes/config.yaml
mcp_servers:
  filip-pajalic-tensorcad:
    command: "npx"
    args: ["-y", "@tensor-cad/mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "filip-pajalic-tensorcad": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@tensor-cad/mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add filip-pajalic-tensorcad -t stdio -c npx -a -y @tensor-cad/mcp
// mcp.json
{
  "mcpServers": {
    "filip-pajalic-tensorcad": {
      "command": "npx",
      "args": [
        "-y",
        "@tensor-cad/mcp"
      ]
    }
  }
}
Changelog

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.

  • 29 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Sept 26 0
    • Known CVEs: pass → unverified ▼ security
    • Dependency health: 1.00 → unverified ▼ functional
    • Package version: 0.1.18 → 0.1.21 functional
    • Package version: 0.1.18 → 0.1.20 functional
    • Package version: 0.1.18 → 0.1.19 functional
  • 25 Sept 26 +27
    • Stability: 0.03 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Known CVEs: unverified → pass ▲ security
    • Malware scan: unverified → pass ▲ security
    • Schema quality: 4746 → 5641 ▼ functional
    • Schema quality: 4746 → 5426 ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Schema quality: 100 → unverified ▼ functional
    • Dependency health: unverified → 1.00 ▲ functional
    • Package version: 0.1.13 → 0.1.18 functional
    • Package version: 0.1.13 → 0.1.17 functional
    • Package version: 0.1.13 → 0.1.16 functional
    • Package version: 0.1.13 → 0.1.15 functional
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Sept 26 −11
    • Known CVEs: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Malware scan: unverified → pass ▲ security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • Capabilities: pass → unverified ▼ functional
    • Dependency health: 1.00 → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Schema quality: 100 → unverified ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • Package version: 0.1.8 → 0.1.13 functional
    • Package version: 0.1.8 → 0.1.12 functional
    • Package version: 0.1.8 → 0.1.11 functional
    • Package version: 0.1.8 → 0.1.10 functional
    • Package version: 0.1.8 → 0.1.9 functional
  • 23 Sept 26 68

    First indexed and scored.

Diagnostics

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 29 Sept 2026 · Analysed npm/@tensor-cad/mcp@0.1.21

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo Filip-Pajalic/TensorCAD
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/Filip-Pajalic/TensorCAD/.github/workflows/release.yml@refs/tags/v0.1.21
Rekor log index 2968738625
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:0855d058084ab1d1863a9a338b5eb885ab610ebddb95dc152c642c477c26d3a190c3a81822a8edfa155a76a6536b9eaedfbee8109c786741fcdeb4b83

Background: How many MCP packages publish verified provenance →

Dependencies 5 packages
Packages resolved 5
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 19 exposed · ~3,713 tokens

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 →

Tool Tokens
tensorcad_analyze ~372

Parameters, FLOPs per token, KV cache, training and serving memory, decode throughput, training cost and Chinchilla position, for a given sequence length, batch, dtype, device, GPU count and parallel plan.

NameTypeReqDescription
Binteger–Micro-batch size.
Sinteger–Source length, for an encoder-decoder: the second sequence its encoder runs along. Defaults to the document's own S; ignored by a design that declares none.
Tinteger–Sequence length. Defaults to the document's own T.
concurrencyinteger–Concurrent sequences when serving.
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
dpinteger–Data parallel degree.
dtypestring–Training dtype. Default bf16.
epinteger–Expert parallel degree.
gpusinteger––
hardwarestring–Hardware id: h100-sxm, h200-sxm, b200, a100-80, rtx5080 or rtx4090. Default h100-sxm.
mfunumber–Model FLOPs utilization, 0..1.
optimizerstring––
packingobject–Training rows packed with documents, for a design whose mask keeps them apart (doc(b, q) == doc(b, kv)). Moves the training figures and the cost, not serving.
ppinteger–Pipeline parallel degree.
recomputestring––
tokensnumber–Training token budget. Defaults to Chinchilla-optimal.
tpinteger–Tensor parallel degree.
zerointeger–ZeRO/FSDP sharding stage.
NameTypeReqDescription
chinchillaobjectyes–
costobjectyes–
design_idstringyes–
errorsarrayyes–
flopsobjectyes–
kvobjectyes–
memoryobjectyes–
namestringyes–
optionsobjectyes–
paramsobjectyes–
revisionintegeryes–
throughputobjectyes–

No examples provided.

tensorcad_apply_ops ~135

Apply a batch of edits to a design. The batch is all-or-nothing: the first rejected operation aborts it and the design is left untouched. Pass expected_revision to be told about a concurrent edit instead of silently overwriting it. Returns the new revision, what changed, and a fresh validation summary.

NameTypeReqDescription
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
expected_revisioninteger–Revision you last read. The call is rejected if the design has moved on.
opsarrayyesEdits applied in order.
NameTypeReqDescription
appliedarrayyesOne line per operation, in order.
design_idstringyes–
namestringyes–
params_activenumberyes–
params_deltanumberyesChange in total parameters caused by this batch.
params_totalnumberyes–
previous_revisionintegeryes–
revisionintegeryes–
validationobjectyes–

No examples provided.

tensorcad_checkpoint ~85

Snapshot a design under a name you can come back to. Take one before an experiment so tensorcad_restore can put it back exactly.

NameTypeReqDescription
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
labelstring–What this snapshot is, e.g. "before widening the FFN".
NameTypeReqDescription
checkpoint_idstringyes–
checkpointsarrayyes–
created_atstringyes–
design_idstringyes–
labelstringyes–
revisionintegeryes–

No examples provided.

tensorcad_diff ~389

What changed between two designs and what it cost: the symbols, blocks and wires that moved, then the parameters, FLOPs, cache and memory. Both sides are measured at one operating point, so the attention terms are comparable. Use it after an edit, or against a preset, to check the change did what was meant.

NameTypeReqDescription
Binteger–Micro-batch size.
Sinteger–Source length, for an encoder-decoder: the second sequence its encoder runs along. Defaults to the document's own S; ignored by a design that declares none.
Tinteger–Sequence length. Defaults to the document's own T.
astringyesThe design to compare from.
bstringyesThe design to compare to.
concurrencyinteger–Concurrent sequences when serving.
dpinteger–Data parallel degree.
dtypestring–Training dtype. Default bf16.
epinteger–Expert parallel degree.
gpusinteger––
hardwarestring–Hardware id: h100-sxm, h200-sxm, b200, a100-80, rtx5080 or rtx4090. Default h100-sxm.
mfunumber–Model FLOPs utilization, 0..1.
optimizerstring––
packingobject–Training rows packed with documents, for a design whose mask keeps them apart (doc(b, q) == doc(b, kv)). Moves the training figures and the cost, not serving.
ppinteger–Pipeline parallel degree.
recomputestring––
tokensnumber–Training token budget. Defaults to Chinchilla-optimal.
tpinteger–Tensor parallel degree.
zerointeger–ZeRO/FSDP sharding stage.
NameTypeReqDescription
astringyes–
atobjectyes–
bstringyes–
blocksobjectyes–
edgesobjectyes–
identicalbooleanyesTrue when nothing structural moved; the numbers may still differ.
metricsarrayyes–
symbolsobjectyes–

No examples provided.

tensorcad_explain ~405

What one block is and what it contributes: its parameters as written and as evaluated, the shape on every port, its share of the model's weights and compute, and its documentation. Use it to answer "why is this block this size" without reading the whole design.

NameTypeReqDescription
Binteger–Micro-batch size.
Sinteger–Source length, for an encoder-decoder: the second sequence its encoder runs along. Defaults to the document's own S; ignored by a design that declares none.
Tinteger–Sequence length. Defaults to the document's own T.
concurrencyinteger–Concurrent sequences when serving.
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
dpinteger–Data parallel degree.
dtypestring–Training dtype. Default bf16.
epinteger–Expert parallel degree.
gpusinteger––
hardwarestring–Hardware id: h100-sxm, h200-sxm, b200, a100-80, rtx5080 or rtx4090. Default h100-sxm.
mfunumber–Model FLOPs utilization, 0..1.
optimizerstring––
packingobject–Training rows packed with documents, for a design whose mask keeps them apart (doc(b, q) == doc(b, kv)). Moves the training figures and the cost, not serving.
pathstringyesFull path of the block, e.g. "layers/block/attn".
ppinteger–Pipeline parallel degree.
recomputestring––
tokensnumber–Training token budget. Defaults to Chinchilla-optimal.
tpinteger–Tensor parallel degree.
zerointeger–ZeRO/FSDP sharding stage.
NameTypeReqDescription
copiesobjectyes–
design_idstringyes–
flops_per_tokennumberyes–
kindstringyes–
parametersarrayyes–
paramsnumberyes–
pathstringyes–
portsobjectyes–
revisionintegeryes–
share_of_flopsnumberyes–
share_of_paramsnumberyes–
summarystring––
typestringyes–

No examples provided.

tensorcad_generate_code ~131

Emit a runnable PyTorch module plus the design document. Without out_dir the file contents come back in the result; with out_dir they are written to disk and only a manifest comes back.

NameTypeReqDescription
class_namestring–Class name for the top-level module.
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
include_smoke_testboolean–Emit a __main__ block that checks the size.
out_dirstring–Directory to write into. Omit to get the contents inline.
NameTypeReqDescription
design_idstringyes–
filesarrayyes–
out_dirstring––
revisionintegeryes–
warningsarrayyes–
wrotebooleanyes–

No examples provided.

tensorcad_get_block ~98

One block of a design: its parameters as written and as resolved, the inferred shape on every port, what each port is wired to, and how many trainable parameters it contributes.

NameTypeReqDescription
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
pathstringyesBlock path from the outline, e.g. "layers/block" or "embed".
NameTypeReqDescription
categorystringyes–
childrenarrayyes–
design_idstringyes–
formulastring––
idstringyes–
inputsarrayyes–
instancesnumberyes–
kindstringyes–
labelstring––
outputsarrayyes–
param_errorsarrayyes–
paramsobjectyes–
params_countnumberyes–
pathstringyes–
resolved_paramsobjectyes–
revisionintegeryes–
summarystringyes–
typestringyes–

No examples provided.

tensorcad_get_design ~110

Read a design. Use format "outline" (the default) first: it is the whole structure, symbol table and edge shapes in a fraction of the tokens. Use format "full" only when you need the literal JSON document.

NameTypeReqDescription
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
formatstring–"outline" is a compact block/edge summary; "full" is the whole document.
NameTypeReqDescription
design_idstringyes–
dirtybooleanyes–
documentobject–The literal design document.
formatstringyes–
namestringyes–
outlineobject––
params_activenumberyes–
params_totalnumberyes–
pathstring––
revisionintegeryes–

No examples provided.

tensorcad_import_hf ~106

Read a Hugging Face `config.json` into a design and save it in this session. Covers the Llama, Mistral, Qwen, Gemma, Mixtral, DeepSeek and GPT-2 families. Anything the importer cannot model faithfully comes back as a warning rather than being approximated silently.

NameTypeReqDescription
configstringyesThe contents of config.json.
namestring–A name for the design; the config's own is used otherwise.
NameTypeReqDescription
design_idstringyes–
namestringyes–
params_totalnumberyes–
warningsarrayyes–

No examples provided.

tensorcad_list_designs ~73

List the designs this server has open, the built-in reference architectures you can start from, and the .tensorcad.json files it can see on disk. Start here when you do not already hold a design_id.

NameTypeReqDescription
include_filesboolean–Also scan the working directory for .tensorcad.json files.
NameTypeReqDescription
designsarrayyes–
filesarrayyes–
presetsarrayyes–

No examples provided.

tensorcad_mup ~179

The same design at several widths, with what to multiply the initialization and the learning rate by at each, following Tensor Programs V. Sweep hyperparameters at the narrow end and carry the answer up: a learning rate tuned at the base rung is the right one at every rung, scaled per class. Every rung is saved as a design of its own, ready to analyze or generate. It does not choose a learning rate; that is what the sweep is for.

NameTypeReqDescription
base_widthnumber–The width the sweep happens at. Omit for the narrowest.
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
widthsarray–The widths to build. Omit to halve the design's own width down to a width worth sweeping at.
NameTypeReqDescription
base_widthnumberyes–
head_dimnumberyesHeld fixed while the width moves: the heads get more numerous, not wider.
notesarrayyes–
rungsarrayyes–
width_symbolstringyes–

No examples provided.

tensorcad_new_design ~261

Create a design from a reference architecture, or an empty one with just the B and T runtime symbols. Returns the design_id every other tool needs.

NameTypeReqDescription
namestring–Name for the new design. Defaults to the preset's name.
presetstring–One of: nano-sort, gpt2-small, gpt2-medium, gpt2-large, gpt2-xl, nanogpt, bloom-7b1, t5-small, flan-t5-base, llama-2-7b, mistral-7b, llama-3-8b, llama-3-70b, llama-3.1-405b, qwen2.5-7b, qwen3-8b, gem…
NameTypeReqDescription
design_idstringyes–
namestringyes–
outlineobjectyes–
params_totalnumberyes–
revisionintegeryes–
sourcestringyes–

No examples provided.

tensorcad_open_design ~61

Load a .tensorcad.json document from disk and return a design_id for it. Opening the same path twice returns the same handle.

NameTypeReqDescription
pathstringyesPath to a .tensorcad.json file, absolute or relative to the server's directory.
NameTypeReqDescription
design_idstringyes–
namestringyes–
params_totalnumberyes–
pathstringyes–
revisionintegeryes–
validationobjectyes–

No examples provided.

tensorcad_plan ~461

Every way of splitting the training across a cluster that fits, least demanding first. Prices data, tensor, pipeline and expert parallelism, the four ZeRO stages, sequence parallelism and the three recompute settings. Memory is the claim and it is arithmetic; which plan is fastest is not claimed, so each one carries a note about what it costs to run.

NameTypeReqDescription
Binteger–Micro-batch size.
Sinteger–Source length, for an encoder-decoder: the second sequence its encoder runs along. Defaults to the document's own S; ignored by a design that declares none.
Tinteger–Sequence length. Defaults to the document's own T.
concurrencyinteger–Concurrent sequences when serving.
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
dpinteger–Data parallel degree.
dtypestring–Training dtype. Default bf16.
epinteger–Expert parallel degree.
gpusintegeryesHow many devices there are.
gpus_per_nodeinteger–Bounds the tensor-parallel degree. Default 8.
hardwarestring–Hardware id: h100-sxm, h200-sxm, b200, a100-80, rtx5080 or rtx4090. Default h100-sxm.
headroomnumber–Fraction of device memory left free. Default 0.1.
limitinteger–How many plans to return. Default 8.
mfunumber–Model FLOPs utilization, 0..1.
optimizerstring––
packingobject–Training rows packed with documents, for a design whose mask keeps them apart (doc(b, q) == doc(b, kv)). Moves the training figures and the cost, not serving.
ppinteger–Pipeline parallel degree.
recomputestring––
tokensnumber–Training token budget. Defaults to Chinchilla-optimal.
tpinteger–Tensor parallel degree.
zerointeger–ZeRO/FSDP sharding stage.
NameTypeReqDescription
budget_bytesnumberyes–
closestobject––
consideredintegeryes–
design_idstringyes–
fitsarrayyes–
hardwarestringyes–
notesarrayyes–
revisionintegeryes–

No examples provided.

tensorcad_restore ~97

Put a design back. With a checkpoint_id it restores that snapshot; without one it undoes the most recent tensorcad_apply_ops batch. Either way the revision moves forward, so a stale expected_revision still fails.

NameTypeReqDescription
checkpoint_idstring–Omit to undo the last batch of edits.
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
NameTypeReqDescription
design_idstringyes–
namestringyes–
params_totalnumberyes–
restored_fromstringyes–
revisionintegeryes–
validationobjectyes–

No examples provided.

tensorcad_save_design ~82

Write a design to disk as .tensorcad.json. Overwrites the file it was opened from unless a path is given.

NameTypeReqDescription
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
pathstring–Where to write. Defaults to the path it was opened from.
NameTypeReqDescription
bytesintegeryes–
design_idstringyes–
pathstringyes–
revisionintegeryes–

No examples provided.

tensorcad_scale ~185

Shrink a design towards a parameter budget while keeping its proportions, and save the result as a new design. Use it to get a bench-sized proxy of a large architecture: the widths and depth move together, the head dimension stays sane, and the result is reported with how close it landed.

NameTypeReqDescription
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
keep_depthboolean–Hold the layer count fixed and move only the width.
target_basisstring–Whether target_params counts the embedding tables. At bench sizes "non-embedding" is usually meant.
target_paramsnumberyesThe parameter count to aim for.
tie_headboolean–Share the output projection with the embedding.
vocabinteger–Replace the vocabulary, for a smaller tokenizer.
NameTypeReqDescription
achievednumberyes–
changesarrayyes–
design_idstringyesThe new design, saved in this session.
fromstringyes–
namestringyes–
notesarrayyes–
targetnumberyes–

No examples provided.

tensorcad_search_catalog ~97

Search the block catalog. Returns each block's parameter schema, port patterns and documentation, which is what you need before adding a block with tensorcad_apply_ops.

NameTypeReqDescription
categorystring–attention, mlp, norm, embedding, container, io, ...
kindstring––
limitinteger–Default 20.
querystring–Substring matched against type, category, summary and formula.
NameTypeReqDescription
blocksarrayyes–
categoriesarrayyes–
totalintegeryesMatches before the limit was applied.

No examples provided.

tensorcad_validate ~386

Run every design rule: shape and symbol errors, kernel-friendly head dimensions, tensor-core multiples, whether training and serving fit the chosen device, Chinchilla sanity and drift from published numbers. Each finding carries a fix hint.

NameTypeReqDescription
Binteger–Micro-batch size.
Sinteger–Source length, for an encoder-decoder: the second sequence its encoder runs along. Defaults to the document's own S; ignored by a design that declares none.
Tinteger–Sequence length. Defaults to the document's own T.
concurrencyinteger–Concurrent sequences when serving.
design_idstringyesHandle returned by tensorcad_new_design or tensorcad_open_design, e.g. "dsn_1".
dpinteger–Data parallel degree.
dtypestring–Training dtype. Default bf16.
epinteger–Expert parallel degree.
gpusinteger––
hardwarestring–Hardware id: h100-sxm, h200-sxm, b200, a100-80, rtx5080 or rtx4090. Default h100-sxm.
mfunumber–Model FLOPs utilization, 0..1.
optimizerstring––
packingobject–Training rows packed with documents, for a design whose mask keeps them apart (doc(b, q) == doc(b, kv)). Moves the training figures and the cost, not serving.
ppinteger–Pipeline parallel degree.
recomputestring––
severitystring–Only return findings at least this bad.
tokensnumber–Training token budget. Defaults to Chinchilla-optimal.
tpinteger–Tensor parallel degree.
zerointeger–ZeRO/FSDP sharding stage.
NameTypeReqDescription
countsobjectyes–
design_idstringyes–
findingsarrayyes–
namestringyes–
okbooleanyes–
params_totalnumberyes–
revisionintegeryes–

No examples provided.

Common questions

What is the io.github.Filip-Pajalic/tensorcad MCP server?

io.github.Filip-Pajalic/tensorcad is an MCP server listed in the public MCP registry as io.github.Filip-Pajalic/tensorcad. Design transformer LLM architectures and report their parameters, FLOPs, memory and cost. This page covers its npm package (@tensor-cad/mcp).

Is the io.github.Filip-Pajalic/tensorcad MCP server safe to use?

io.github.Filip-Pajalic/tensorcad scores 86 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 29 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 io.github.Filip-Pajalic/tensorcad MCP server expose?

io.github.Filip-Pajalic/tensorcad exposes 19 tools: tensorcad_list_designs, tensorcad_new_design, tensorcad_open_design, tensorcad_save_design, tensorcad_get_design, and 14 more. Their descriptions and schemas cost roughly 3,713 tokens of context every time the server is loaded.

Is the io.github.Filip-Pajalic/tensorcad MCP server still maintained?

io.github.Filip-Pajalic/tensorcad is still listed as active in the MCP registry. We last reached this channel on 29 September 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 io.github.Filip-Pajalic/tensorcad MCP server under?

io.github.Filip-Pajalic/tensorcad declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.