CAD MCP Server
NPM · CAD-MCP-SERVER · SCANNED SEP 21
STEP file inspection for AI. Measure walls, draft angles, clearances. Returns facts, not guesses.
Available components
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 Security90
- No malware found by supply-chain analysis.Pass
- Known CVEs were checked across the 2 of 3 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
- No install/post-install scripts declared.Pass
- Dependency health was assessed across the 2 of 3 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to mattmohandiss/cad-mcp-server). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 74 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability81
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1294 tokens (~143/item across 9 items; 8 tools + 1 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 Management97
- Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 82% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 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
How do I install the CAD MCP Server server?
CAD MCP Server runs locally as an npm package, launched with npx -y cad-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · cad-mcp-server
claude mcp add mattmohandiss-cad-mcp-server -- npx -y cad-mcp-server
{
"mcpServers": {
"mattmohandiss-cad-mcp-server": {
"command": "npx",
"args": [
"-y",
"cad-mcp-server"
]
}
}
} {
"servers": {
"mattmohandiss-cad-mcp-server": {
"command": "npx",
"args": [
"-y",
"cad-mcp-server"
]
}
}
} codex mcp add mattmohandiss-cad-mcp-server -- npx -y cad-mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mattmohandiss-cad-mcp-server": {
"type": "local",
"command": [
"npx",
"-y",
"cad-mcp-server"
],
"enabled": true
}
}
} openclaw mcp add mattmohandiss-cad-mcp-server --command npx --arg -y --arg cad-mcp-server
mcp_servers:
mattmohandiss-cad-mcp-server:
command: "npx"
args: ["-y", "cad-mcp-server"] {
"McpServers": {
"mattmohandiss-cad-mcp-server": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"cad-mcp-server"
]
}
}
} assistant mcp add mattmohandiss-cad-mcp-server -t stdio -c npx -a -y cad-mcp-server
{
"mcpServers": {
"mattmohandiss-cad-mcp-server": {
"command": "npx",
"args": [
"-y",
"cad-mcp-server"
]
}
}
} 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 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 −3
- Security disclosure: unverified → pass ▲ functional
- Stability: pass → 0.80 functional
- 15 Sept 26 0
- Stability: 0.97 → pass security
- Security disclosure: pass → unverified ▼ functional
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
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 Sept 2026 · Analysed npm/cad-mcp-server@0.6.1
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 | mattmohandiss/cad-mcp-server |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/mattmohandiss/cad-mcp-server/.github/workflows/release-please.yml@refs/heads/main |
| Rekor log index | 2118578286 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:4c17785f753313f534bd618ef039addb2e994cae984798b630b56b8aaa38fd51c9364237f8b57513b9e707277f7343ade8395300095a0ba26af0d856b |
Background: How many MCP packages publish verified provenance →
Dependencies 2 packages
| Packages resolved | 2 |
|---|---|
| Tree resolution | Partial |
The dependency tree was only partially resolved, so these counts may be incomplete.
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 →
diff_step ~62
Compare two STEP files. Returns deltas: volume, surface area, dimensions, face/edge/body counts. Comparison minus baseline.
| Name | Type | Req | Description |
|---|---|---|---|
| baseline_file_path | string | yes | Path to baseline STEP file. |
| comparison_file_path | string | yes | Path to comparison STEP file. |
No output schema declared.
No examples provided.
find_edges ~98
Find edges by curve type, length, radius, or dihedral angle. Returns IDs, curve types, lengths, radii, diameters. Use returned IDs in measure_distance or measure_geometry.
| Name | Type | Req | Description |
|---|---|---|---|
| file_path | string | yes | Path to STEP file on local filesystem. |
| filters | object | – | – |
| include | array | – | – |
| max_results | integer | – | – |
| sort | string | – | – |
| summarize | object | – | – |
No output schema declared.
No examples provided.
find_faces ~129
Find faces by type, area, radius, normal, quality, or body. Returns IDs, surface types, areas, radii, diameters, axes, normals. Use returned IDs in measure_distance, measure_thickness, measure_draft, or measure_geometry.
| Name | Type | Req | Description |
|---|---|---|---|
| file_path | string | yes | Path to STEP file on local filesystem. |
| filters | object | – | – |
| include | array | – | Result detail presets. Omit for basic face identity, area, bounds, and adjacency. |
| max_results | integer | – | – |
| sort | string | – | – |
| summarize | object | – | – |
No output schema declared.
No examples provided.
inspect_step ~91
Use this FIRST for a compact model overview: dimensions, bounding box, body/face/edge counts, validity, watertight status. Use include[] for bodies, quality, pmi, inertia, or topology detail.
| Name | Type | Req | Description |
|---|---|---|---|
| file_path | string | yes | Path to STEP file on local filesystem. |
| include | array | – | Detail presets. Default: size, counts, health. Add more for detailed analysis. |
No output schema declared.
No examples provided.
measure_distance ~178
Measure distance between entity sets. Pass sources[] and targets[] for set-based measurement (e.g. clearance between holes and walls). Use summary="minimum" for the closest pair only.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_ids | array | – | Source entity IDs (legacy mode with target_entity_id). Prefer sources/targets for set mode. |
| file_path | string | yes | Path to STEP file on local filesystem. |
| include_extrema | boolean | – | Include closest point pairs with coordinates. |
| sources | array | – | Source entity IDs for set-based distance. Use with targets for clearance checks. |
| summary | string | – | all = return every pair; minimum = return only the closest pair. |
| target_entity_id | string | – | Single target entity ID. Use when sources is omitted with entity_ids. |
| targets | array | – | Target entity IDs for set-based distance. |
No output schema declared.
No examples provided.
measure_draft ~122
Measure draft angles of faces relative to a pull direction. Returns draft_angle_deg, normal, and undercut flag per face. Positive = good for ejection; negative = undercut.
| Name | Type | Req | Description |
|---|---|---|---|
| faces | array | yes | Face IDs to check draft angle on. |
| file_path | string | yes | Path to STEP file on local filesystem. |
| pull_direction | array | – | Pull direction [x,y,z]. Mutually exclusive with pull_direction_mode. |
| pull_direction_mode | string | – | Direction shortcut. axis = along the face axis; normal = along the face normal. |
No output schema declared.
No examples provided.
measure_geometry ~407
Ray tests, point analysis, cross-sections, and edge continuity. measurement_type selects the operation: ray, ray_grid, point_analysis, section, or continuity.
| Name | Type | Req | Description |
|---|---|---|---|
| analyze | string | – | Section analysis mode. edge_count = count and describe edges; thickness = measure section thickness. |
| bidirectional | boolean | – | Fire rays in both directions. Used by ray_grid. |
| checks | array | – | Checks to perform at each point. Required for point_analysis. |
| detail | string | – | stats = min/max/avg; samples = hit coordinates; hits = full grid results. |
| direction | array | – | Ray direction [x,y,z]. Used by ray, ray_grid. |
| direction_mode | string | – | Direction shortcut. axis = along entity axis; normal = along entity normal. |
| entity_ids | array | yes | Entity IDs from find_faces/find_edges or inspect_step bodies. |
| file_path | string | yes | Path to STEP file on local filesystem. |
| max_distance | number | – | Maximum ray distance mm. If set, ray becomes bounded (ray_test_segment). |
| measurement_type | string | yes | ray = single ray from origin in direction; ray_grid = grid of rays across entity; point_analysis = classify/project/curvature at points; section = planar cross-section; continuity = edge smoothness b… |
| origin | array | – | Ray origin [x,y,z]. Used by ray. Mutually exclusive with origin_mode. |
| origin_mode | string | – | Origin shortcut relative to entity bounding box. Used by ray. |
| plane_normal | array | – | Normal of cutting plane. Required for section. |
| plane_origin | array | – | Point on cutting plane. Required for section. |
| points | array | – | 3D points to analyze. Required for point_analysis. |
| spacing_mm | number | – | Grid spacing mm. Used by ray_grid. Default 2. |
| tolerance | number | – | Tolerance mm for point checks. Default 0.01. |
No output schema declared.
No examples provided.
measure_thickness ~172
Measure wall thickness across faces via ray grid sampling. Returns min/max/avg thickness per face. Use direction_mode="normal" (default) or direction_mode="axis".
| Name | Type | Req | Description |
|---|---|---|---|
| bidirectional | boolean | – | Fire rays in both directions. Default true for thickness. |
| detail | string | – | stats = min/max/avg only; samples = include hit coordinates. |
| direction | array | – | Ray direction [x,y,z]. Mutually exclusive with direction_mode. |
| direction_mode | string | – | Direction shortcut. axis = along the face axis; normal = along the face normal. |
| faces | array | yes | Face IDs to measure wall thickness across. |
| file_path | string | yes | Path to STEP file on local filesystem. |
| spacing_mm | number | – | Grid spacing in mm. Smaller = denser sampling. |
No output schema declared.
No examples provided.
What is the CAD MCP Server server?
CAD MCP Server is listed in the public MCP registry as io.github.mattmohandiss/cad-mcp-server. STEP file inspection for AI. Measure walls, draft angles, clearances. Returns facts, not guesses. This page covers its npm package (cad-mcp-server).
Is the CAD MCP Server server safe to use?
CAD MCP Server scores 93 out of 100 on VerifyMCP. 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 CAD MCP Server server expose?
CAD MCP Server exposes 8 tools: inspect_step, find_faces, find_edges, measure_distance, measure_thickness, and 3 more. Their descriptions and schemas cost roughly 1,259 tokens of context every time the server is loaded.
Is the CAD MCP Server server still maintained?
CAD MCP Server is still listed as active in the MCP registry. We last reached this channel on 21 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 CAD MCP Server server under?
CAD MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.