MCP server that generates quality control plans and inspection reports from technical-drawing PDFs — tolerances, fits, threads, GD&T and surface finishes extracted automatically, balloon numbering, acceptance limits, ballooned drawing PDF and Excel measurement report. By Imnoo, powers quality-check-protocol.imnoo.com.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add quality-control-plan-mcp -- npx -y quality-control-plan-mcp{
"mcpServers": {
"quality-control-plan-mcp": {
"command": "npx",
"args": ["-y", "quality-control-plan-mcp"]
}
}
}MCP Servers overview
# Quality Control Plan MCP Server
[](https://glama.ai/mcp/servers/imnoo-team/quality-control-plan-mcp)
**Generate quality control plans and inspection reports from technical-drawing PDFs — from any MCP-enabled assistant.**
This [Model Context Protocol](https://modelcontextprotocol.io) server exposes the engine behind [quality-check-protocol.imnoo.com](https://quality-check-protocol.imnoo.com) (by [Imnoo](https://www.imnoo.com)). Need a quality control plan for a technical drawing? Hand the PDF to your assistant and get a numbered inspection plan in about a minute: every dimensional tolerance, ISO fit, thread, geometric tolerance (GD&T) and surface finish is extracted automatically by Imnoo's drawing analysis, ballooned on the drawing and listed with its acceptance limits — ⌀50 ±0.05 becomes 49.95–50.05 — and a measuring instrument. Ask for an inspection class (100 % full inspection, Q1 reduced, Q2 spot check), keep the balloon numbers printed on the drawing or renumber them (1, 001 or D001 style, in reading or measurement order), then let it write the ballooned drawing, the complete inspection package or the Excel measurement and inspection report — the same documents the Imnoo calculator produces. It covers first-article inspection, PPAP-style dimensional reports and shop-floor quality check protocols, on vector and scanned PDFs alike. Built by Imnoo, the planning, scheduling and quoting platform for CNC manufacturers — where the same quality check protocols come out of every quote, next to cost estimation, manufacturing plans and G-code generation.
```
"Create a Q1 quality plan for flange.pdf with type-prefixed balloon numbers"
│
▼ (your assistant calls the tools)
analyze_drawing ──► build_quality_plan ──► export_inspection_pdf + export_quality_plan_excel
│
▼
QP-1001-A_inspection-package.pdf D001 ⌀50 (±0.05) 49.95–50.05 Caliper
QP-1001-A_Q1.xlsx H001 ⌀10 H7 — Inside micrometer
G001 ⏥ 0.05 — CMM
```
## Tools
| Tool | What it does |
| --- | --- |
| `analyze_drawing` | Uploads a drawing PDF (vector or scanned, ≤ 30 MB) to Imnoo's drawing analysis — the service behind the web app — and returns every detected characteristic with type, value, PDF page, position, confidence and the balloon number printed on the drawing, plus the title block (drawing / article number, material, general tolerance). `save_analysis_to` keeps the analysis JSON for offline reuse. |
| `load_analysis` | Opens a saved analysis JSON. Fully offline — no upload, no daily credit. |
| `build_quality_plan` | Turns the analysis into the plan: balloon numbers (numeric, `001` padded, or type-prefixed `D001` / `H001` / `G001`…; printed numbers kept, or renumbered by list, reading direction or measurement sequence), acceptance limits from nominal ± tolerance, a default measuring instrument per type, inspection-class presets, selection presets (first-article = everything, production = measurable characteristics only) and per-row edits. Deterministic — iterate freely. |
| `export_quality_plan_excel` | Writes the *Measurement and inspection report* workbook: header block (article, ET-No., batch, inspection rate), visual-inspection checklist a–e, dimensional-conformity table (Insp. dim. no. · nominal dimension or thread size · tolerance range · measuring instrument · actual dimension · deviation · date · inspector), change-tracking footnotes and the special-release / signature block. Cell for cell the report the Imnoo calculator produces. |
| `export_inspection_pdf` | Writes the ballooned drawing (`ballooned`), the drawing plus the printed plan (`package`, default) or the plan document alone (`plan`): translucent boxes on every selected characteristic, numbered balloons with optional VDA-style leader arrows, the two-column general-information form, the feature table with colored number chips, instrument / sample fill-in lines, acceptance criteria and result checkboxes, and the final-approval block. The source PDF is never modified. |
Plus a `create-quality-plan` prompt that walks the assistant through analyze → review → export.
**Where the analysis runs.** `analyze_drawing` is the only tool that leaves your machine: it uploads the PDF to Imnoo's drawing analysis exactly like the web app does — **1 free analysis per day per IP address** (more when signed in), uploaded files are deleted automatically after a short retention period, nothing else is stored. Everything after that — plan building, numbering, acceptance limits, Excel and PDF generation — runs locally and offline.
## Installation
Requires Node.js ≥ 18.
### Claude Code
```bash
claude mcp add quality-control-plan -- npx -y quality-control-plan-mcp
```
### Claude Desktop
Add to `claude_desktop_config.json` (Settings → Developer → Edit Config):
```json
{
"mcpServers": {
"quality-control-plan": {
"command": "npx",
"args": ["-y", "quality-control-plan-mcp"]
}
}
}
```
### Cursor
[**Add to Cursor**](cursor://anysphere.cursor-deeplink/mcp/install?name=quality-control-plan&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsInF1YWxpdHktY29udHJvbC1wbGFuLW1jcCJdfQ==) — or add to `~/.cursor/mcp.json`:
```json
{
"mcpServers": {
"quality-control-plan": {
"command": "npx",
"args": ["-y", "quality-control-plan-mcp"]
}
}
}
```
### VS Code (GitHub Copilot)
```bash
code --add-mcp '{"name":"quality-control-plan","command":"npx","args":["-y","quality-control-plan-mcp"]}'
```
### Windsurf / other stdio clients
Any client that launches stdio servers works with:
```
npx -y quality-control-plan-mcp
```
### Configuration (optional)
| Variable | Purpose |
| --- | --- |
| `IMNOO_ACCESS_TOKEN` | Your Imnoo account token (the id token of your [quality-check-protocol.imnoo.com](https://quality-check-protocol.imnoo.com) login) — raises the daily analysis limit to your plan's quota. |
| `QCP_APP_URL` | Point the analysis at another deployment of the web app (default `https://quality-check-protocol.imnoo.com`). |
## Example session
> **You:** Build a Q1 quality plan for `C:\drawings\flange.pdf` with type-prefixed numbers and write everything next to the drawing.
>
> **Assistant:** *calls `analyze_drawing`* — 17 characteristics on 2 pages: 5 dimensional tolerances, 2 drill fits (⌀10 H7 carries the printed balloon 1), 1 shaft fit, 2 threads, 1 fine thread, 2 geometric tolerances, 4 surface finishes; drawing QP-1001-A, article 4711-050, AlMg3, ISO 2768-mK. *calls `build_quality_plan` with `inspection_class: "Q1"` and `numbering: { style: "typePrefixed" }`* — D001 ⌀50 (±0.05) → 49.95–50.05 (Caliper), H001 ⌀10 H7 (Inside micrometer), G001 ⏥ 0.05 (CMM), R001 Ra 3.2 (Surface roughness gauge)… *calls `export_inspection_pdf` and `export_quality_plan_excel` with the same plan* — wrote `QP-1001-A_inspection-package.pdf` (both drawing pages ballooned + the printed plan) and `QP-1001-A_Q1.xlsx`. Two values on page 2 were read with low confidence — worth a glance before the plan goes to the shop floor.
Those numbers are the bundled sample drawing the smoke test runs against; real drawings vary.
## Plan options (the `plan` argument)
One object, accepted by `build_quality_plan` and both export tools — pass the same one everywhere so the documents match the reviewed plan. Everything is optional; the defaults reproduce the web app's initial plan.
| Option | Values |
| --- | --- |
| `numbering.style` | `numeric` (default), `padded` (`001`), `typePrefixed` (`D001` dimensional, `H` drill fit, `S` shaft fit, `T` thread, `F` fine thread, `G` geometric, `R` surface roughness, `L` length) |
| `numbering.order` | `custom` (default — balloon numbers printed on the drawing are kept, the rest fill up), `list` (plan-table order), `reading` (top-left → bottom-right, page by page), `measurement` (CMM-measured geometric tolerances first, surface finishes last) |
| `numbering.restart_per_type` | restart the counter for every characteristic type |
| `section_order` | e.g. `["dimensional", "geometric"]` — listed types first, the rest in the default measurement sequence |
| `selection` · `include` · `exclude` | `all` (default), `production` (dimensional, fits, geometric — no threads or surface finishes), `none`; or explicit feature ids |
| `inspection_class` | `100%` (rate 100 %, checklist on), `Q1` (10 %, checklist on), `Q2` (5 %, checklist off), or any custom class name |
| `header` | `batch_number`, `inspection_rate`, `inspection_class`, `inspector_name`, `signature`, `date` |
| `drawing` · `article_name` · `drawing_index` | title-block values to print when the analysis missed them (article / drawing number, material, general tolerance, article name, revision) |
| `default_tools` | measuring instrument per type — defaults: CMM, thread plug gauge, caliper, inside / outside micrometer, depth caliper, surface roughness gauge |
| `rows[]` | per characteristic (by `feature_id`): `inspection_tool`, `samples` (judged against the limits), `passed`, `balloon`, `value` (corrected value; the original is kept as a footnote) |
| `include_checklist` · `show_arrows` · `annotation` | Excel checklist toggle, leader arrows on the drawing, an "INSPECTION DRAWING" stamp block (revision, note) |
## How the plan is derived
- Acceptance limits exist for plain dimensional tolerances with a numeric nominal (nominal + lower / upper deviation, rounded to 2 decimals). Fits, threads, geometric tolerances and surface finishes are gauged rather than measured against limits — the same rule as the Imnoo calculator.
- Balloon numbers are derived from the selection and the numbering settings, so dropping a characteristic renWhat people ask about quality-control-plan-mcp
What is imnoo-team/quality-control-plan-mcp?
+
imnoo-team/quality-control-plan-mcp is mcp servers for the Claude AI ecosystem. MCP server that generates quality control plans and inspection reports from technical-drawing PDFs — tolerances, fits, threads, GD&T and surface finishes extracted automatically, balloon numbering, acceptance limits, ballooned drawing PDF and Excel measurement report. By Imnoo, powers quality-check-protocol.imnoo.com. It has 0 GitHub stars and its last recorded update is dated 2026-09-11.
How do I install quality-control-plan-mcp?
+
You can install quality-control-plan-mcp by cloning the repository (https://github.com/imnoo-team/quality-control-plan-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is imnoo-team/quality-control-plan-mcp safe to use?
+
Our security agent has analyzed imnoo-team/quality-control-plan-mcp and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains imnoo-team/quality-control-plan-mcp?
+
imnoo-team/quality-control-plan-mcp is maintained by imnoo-team. The last recorded GitHub activity is dated 2026-09-11, with 0 open issues.
Are there alternatives to quality-control-plan-mcp?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy quality-control-plan-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/imnoo-team-quality-control-plan-mcp)<a href="https://claudewave.com/repo/imnoo-team-quality-control-plan-mcp"><img src="https://claudewave.com/api/badge/imnoo-team-quality-control-plan-mcp" alt="Featured on ClaudeWave: imnoo-team/quality-control-plan-mcp" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!