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.

TechDraw AI

NPM · TECHDRAWAI-MCP · SCANNED SEP 22

Photo to technical drawing, CAD-ready DXF and DWG, 3D models and product renders.

Available components

npm · techdrawai-mcp 82
+1 this week 82 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 Security98
  • 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
  • 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability67
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1484 tokens (~247/item across 6 items; 6 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 Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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 Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the TechDraw AI MCP server?

TechDraw AI runs locally as an npm package, launched with npx -y techdrawai-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 · techdrawai-mcp

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

  • 22 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.

  • 21 Sept 26 0
    • Security disclosure: unverified → fail ▼ functional
  • 20 Sept 26 0
    • Security disclosure: fail → unverified ▼ functional
  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −2
    • Stability: pass → 0.83 functional
  • 17 Sept 26 0
    • Stability: 0.97 → pass security
  • 16 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.

  • 14 Sept 26 0
    • Security disclosure: unverified → fail ▼ functional
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 22 Sept 2026 · Analysed npm/techdrawai-mcp@0.1.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 96 packages
Packages resolved 96
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~1,484 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
check_credits ~38

The authenticated account's credit balance, plan, and what each operation costs. Call it before a batch so you know how far the balance goes.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

generate_technical_drawing ~504

Turn a photograph of a physical object into a dimensioned, standards-compliant 2D technical drawing (orthographic views, dimension lines, projection symbol). Supply the photo as a local file path, an http(s) URL or a data URL. Either let the model estimate real-world dimensions, or pass measurements you actually took so the drawing is anchored to real sizes. Choose the drafting standard (ISO/ANSI), sheet size, projection angle, drawing type and which views to include. Costs 3 credits. The drawing image is saved to disk and its path returned — feed that path to `image_to_dxf` for CAD geometry, or to `render_product` for a photoreal render.

NameTypeReqDescription
drawing_typestring–working = fully dimensioned production drawing (default); assembly = numbered balloons + parts list; as-fitted = record of the item as built; patent = numbered figure, no dimensions.
estimate_dimensionsboolean–Let the model infer realistic real-world dimensions. Defaults to true when no measurements are given, false when they are.
imagestringyesThe product photo: a local file path, an http(s) URL, or a data:image/…;base64,… URL.
measurementsarray–Dimensions actually measured on the object. Every other feature is scaled proportionally from these, so one accurate measurement makes the whole drawing accurate.
notesstring–Anything else to state on the drawing (material, finish, tolerances).
output_pathstring–Where to save the drawing. Defaults to ./techdrawai-output/drawing-<timestamp>.png.
paper_sizestring–Sheet size: A4/A3/A2/A1/A0 for ISO (default A3), or "ANSI A"…"ANSI E" for ANSI (default "ANSI B").
product_namestring–What the object is, e.g. "oak dining chair". Improves the title block and the estimated dimensions. Use `identify_product` first if you do not know.
projectionstring–Projection angle. first-angle (default, ISO/Europe) or third-angle (ANSI/North America).
standardstring–Drafting standard. ISO (default) or ANSI.
unitsstring–Primary drawing unit. Defaults to mm.
viewsarray–Which views to include. Defaults to front, top and side.

No output schema declared.

No examples provided.

identify_product ~93

Name the main object in a photo with a short, specific label (e.g. "L-shaped wall bracket"). Free — no credits. Use it to fill in `product_name` before generating a drawing, which improves both the title block and the estimated dimensions.

NameTypeReqDescription
imagestringyesThe photo: a local file path, an http(s) URL, or a data:image/…;base64,… URL.

No output schema declared.

No examples provided.

image_to_dxf ~326

Trace a raster image — a generated technical drawing, a scan, a sketch, a logo — into real CAD vector contours and write a DXF file. The DXF opens in AutoCAD, Fusion 360, SolidWorks, Onshape, FreeCAD, LibreCAD, Inkscape and the common laser/CNC tools. Set `width_mm` to bring the geometry in at a real-world size instead of one unit per pixel. Set `dwg: true` to also get AutoCAD's native DWG. Free — no credits. Returns the paths of the files written.

NameTypeReqDescription
dwgboolean–Also convert to DWG (AutoCAD's native format).
imagestringyesThe image to trace: a local file path, an http(s) URL, or a data:image/…;base64,… URL.
invertboolean–Trace light lines on a dark background.
output_pathstring–Where to save the .dxf. Defaults to ./techdrawai-output/drawing-<timestamp>.dxf. Any DWG is written beside it.
smoothingnumber–1 (default) keeps detail; higher values smooth the contours.
threshold––Luminance cut-off between ink and paper. "auto" (default) picks it from the image, which is what photos and shaded renders need. Give a number to force it.
width_mmnumber–Real-world width of the result in millimetres. Omit to get one DXF unit per traced pixel.

No output schema declared.

No examples provided.

photo_to_3d ~216

Turn a photograph of a single object into a textured 3D mesh, downloadable as GLB (and FBX, OBJ, USDZ, STL). Reconstruction is asynchronous on the server and typically takes one to three minutes — the call blocks until the mesh is ready. Needs a clear photo of one object, as JPG or PNG. Costs 3 credits and requires the Studio plan. The GLB is downloaded to disk and its path returned.

NameTypeReqDescription
detailstring–Mesh density: draft (12k triangles), standard (40k, default) or high (80k). Barely affects generation time.
imagestringyesThe product photo (JPG or PNG): a local file path, an http(s) URL, or a data:image/…;base64,… URL.
output_pathstring–Where to save the .glb. Defaults to ./techdrawai-output/model-<timestamp>.glb.
texturedboolean–Generate colour textures. Defaults to true.

No output schema declared.

No examples provided.

render_product ~307

The reverse of drafting: take a 2D technical drawing and produce a photorealistic image of the finished, manufactured product. The geometry is reconstructed from the views in the drawing, so the render matches the design rather than inventing a new one. Choose the look (photoreal, studio, matte clay, lifestyle), the background, the camera angle and the material/finish. Costs 3 credits. The render is saved to disk and its path returned.

NameTypeReqDescription
anglestring–Camera angle. Defaults to three-quarter.
backgroundstring–white (default), gradient, or scene (in context).
imagestringyesThe technical drawing: a local file path, an http(s) URL, or a data:image/…;base64,… URL. The output of `generate_technical_drawing` works directly.
materialstring–Material and finish, e.g. "brushed aluminium, matte black".
notesstring–Anything else to emphasise.
output_pathstring–Where to save the render. Defaults to ./techdrawai-output/render-<timestamp>.png.
product_namestring–What the object is, e.g. "wall bracket". Helps the reconstruction.
stylestring–photoreal = a convincing real photo (default); studio = catalogue lighting on a seamless backdrop; clay = neutral grey to read form; lifestyle = the product in a real setting.

No output schema declared.

No examples provided.

Common questions

What is the TechDraw AI MCP server?

TechDraw AI is an MCP server listed in the public MCP registry as io.github.MeltFlexDevs/techdrawai. Photo to technical drawing, CAD-ready DXF and DWG, 3D models and product renders. This page covers its npm package (techdrawai-mcp).

Is the TechDraw AI MCP server safe to use?

TechDraw AI scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 September 2026. It declares no install or post-install scripts. 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 TechDraw AI MCP server expose?

TechDraw AI exposes 6 tools: generate_technical_drawing, render_product, image_to_dxf, photo_to_3d, identify_product, check_credits. Their descriptions and schemas cost roughly 1,484 tokens of context every time the server is loaded.

Is the TechDraw AI MCP server still maintained?

TechDraw AI is still listed as active in the MCP registry. We last reached this channel on 22 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 TechDraw AI MCP server under?

TechDraw AI declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.