Partreel

Name: Partreel
Author: mingyo186

by mingyo186version 1.0.0i★ –iRuns in the cloud

Registry nameio.github.mingyo186/partreel

Install

Overview

Description from the maker (original English)

Verified KiCad footprints, symbols & 3D models for AI agents. No signup, CC-BY-4.0, quality-gated.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
UsageiNot measured yet★ –

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs in the cloud
Transport: Streamable HTTP
Category: Design, images & audio

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 1 passed
Runs on the maker’s server: what you ask it goes through their server.
The registry lists no key to fill in.

You need

Runs in the cloudNothing to install; it connects over the internet

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Works in Claude on the web, desktop and mobile:

Open Settings → Connectors
Press Add custom connector
Paste the address below and press Add
If it asks you to sign in, sign in with the maker

https://mcp.partreel.com/mcp

Run this in your terminal

claude mcp add --transport http partreel https://mcp.partreel.com/mcp

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "partreel": {
      "url": "https://mcp.partreel.com/mcp"
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "partreel": {
      "type": "http",
      "url": "https://mcp.partreel.com/mcp"
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

ChatGPT connects only to servers on the internet:

Open ChatGPT on the web → Settings → Connectors (Apps)
Press Create or Add (some plans need Developer mode under Advanced first)
Paste the address below, give it a name and save
If it asks you to sign in, sign in with the maker

https://mcp.partreel.com/mcp

Menu names can differ slightly by plan and over time.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

We have not read this server’s tool list yet; we check endpoints in rotation.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account mingyo186, which owns the repo
… Not checked yet
Still maintained
We have not read this repo from GitHub yet
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
… Not checked yet
Endpoint responds
Not checked yet; we check endpoints in rotation
… Not checked yet
Sign-in with OAuth
Not checked yet; we check endpoints in rotation
… Not checked yet
No hidden instructions in tool descriptions
Not checked yet; we read the tool list when we check the endpoint

Compared with others in Design, images & audioi

More stars than 0% of the other 2204 servers in this category
Published to the registry more recently than 14% of the other 2204 servers in this category
Basic checks equal to or better than 100% of the other 2204 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Partreel safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.

Is it still maintained?

The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 4 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.

What can I use instead?

In the same category: Figma Context MCP, Claude Real Video, Figma MCP Server

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Figma Context MCP

by GLips

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

Runs on your computer★ 16,165MITUpdated 5 months ago

Install

Claude Real Video

by HUANGCHIHHUNGLeo

Let any LLM watch a video locally — and search everything it has ever watched.

Runs on your computer★ 2,284MITUpdated 2 months ago

Install

Figma MCP Server

by figma

Figma’s official server gives AI your design data so it can turn designs into code or describe them accurately. Connects to Figma’s cloud.

Runs in the cloud★ 2,152Updated 13 months ago

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

PartReel — open KiCad parts registry for humans & AI agents

No login. No paywall. Machine-verified. Every part ships as a bundle of KiCad footprint (.kicad_mod) + symbol (.kicad_sym) + 3D model (STEP + GLB), generated from manufacturer-datasheet dimensions and checked by automated quality gates on every deploy.

Site: https://partreel.com · API: https://partreel.com/api/ · MCP server: https://mcp.partreel.com/mcp · Agent guide: https://partreel.com/agents/

Why this exists

The official KiCad library is excellent — use it when it has your part. PartReel focuses on parts the official library doesn't cover (checked against GitLab master before we add anything).
Aggregator sites lock downloads behind sign-ups; agents and scripts can't use them. Everything here is a plain URL.
AI agents regenerate footprints from scratch every time — wasteful and unverified. PartReel is the place to fetch a verified part instead, and report back (field_reports in the API).

Provenance — verify us, don't trust us

Every part's API entry (/api/v1/parts/ .json) carries machine-readable provenance: the exact datasheet figure/table each dimension came from (dimensions_source), the generator source file in this repo, the quality gates it passed, and field-usage reports. Gates run in CI on every push and block deployment on failure — see .github/workflows/deploy.yml.

Gate	Checks
`validate_kicad.py`	s-expression structure, pads, layers, pin-1
KLC drawing rules	silk 0.12 / fab 0.10 + pin-1 chamfer / courtyard 0.05
`check_overlap.py`	no overlapping text in previews
`check_render.py`	files exist, SVG pads/outlines match source, pages/API present, datasheet cited
`check_zfight.py`	no coplanar z-fighting faces, pins are individual bodies
`validate_step.py`	STEP solids pass FreeCAD kernel isValid

For AI agents

Static JSON API, no auth, no rate limit: /api/v1/parts.json
Remote MCP server (nothing to install): claude mcp add --transport http partreel https://mcp.partreel.com/mcp — tools: search_parts, get_part, list_parts, submit_part, report_feedback, request_part, how_to_contribute
Machine guide: /llms.txt
The loop: search → use → if a part is missing, build it from the datasheet and submit_part — it is shared with every agent instantly (labeled unverified/staging), then hourly CI gates + review promote it to verified.
request_part generates parametric families (pin headers, LDOs) server-side in ~5 min; the PR path (CONTRIBUTING-AGENTS.md) remains for 3D models and edits.

Repository layout

library/                 part assets (CC-BY-4.0): .kicad_mod / .kicad_sym / .step / .glb / meta.json

generators/ parametric generators (Python; KiCad text + FreeCAD 3D) + quality gates api/, p/, assets/ static site & JSON API (built by CI) mcp/ Cloudflare Worker MCP server

License

Code (generators, site): MIT
Part assets (library/): CC-BY-4.0

Dimensions come from manufacturer datasheets and are provided as-is; verify before manufacturing.

Credits

Bug reports are contributions. Reporters whose feedback led to a fix are recorded in CREDITS.md and in the fix commits as Reported-by:; imported-library authors are credited in ATTRIBUTIONS.md.

Parts index

Currently 18258 parts, all machine-verified (structure, KLC drawing rules, render completeness, 3D coplanar/merged-pin checks, STEP kernel) with datasheet-cited dimensions.

connector (4330)

Part	MPN	Manufacturer	Files
004500 (CERN library)	`004500`	ERNI	cern_erni_004500
02 01 160 2101 (CERN library)	`02 01 160 2101`	HARTING	cern_harting_02_01_160_2101
02 01 160 2102 (CERN library)	`02 01 160 2102`	HARTING	cern_harting_02_01_160_2102
02 02 160 2201 (CERN library)	`02 02 160 2201`	HARTING	cern_harting_02_02_160_2201
02 02 160 2301 (CERN library)	`02 02 160 2301`	HARTING	cern_harting_02_02_160_2301
02 04 160 1101 (CERN library)	`02 04 160 1101`	HARTING	cern_harting_02_04_160_1101
02 07 160 1101 (CERN library)	`02 07 160 1101`	HARTING	cern_harting_02_07_160_1101
031-6575 (CERN library)	`031-6575`	AMPHENOL-RF	cern_amphenol_031_6575
054392 (CERN library)	`054392`	ERNI	cern_erni_054392
054546 (CERN library)	`054546`	ERNI	cern_erni_054546
054594 (CERN library)	`054594`	ERNI	cern_erni_054594
054595 (CERN library)	`054595`	ERNI	cern_erni_054595
054596 (CERN library)	`054596`	ERNI	cern_erni_054596
063197 (CERN library)	`063197`	ERNI	cern_erni_063197
063209 (CERN library)	`063209`	ERNI	cern_erni_063209
063210 (CERN library)	`063210`	ERNI	cern_erni_063210
064317 (CERN library)	`064317`	ERNI	cern_erni_064317
064318 (CERN library)	`064318`	ERNI	cern_erni_064318
064321 (CERN library)	`064321`	ERNI	cern_erni_064321
09 02 164 2921 (CERN library)	`09 02 164 2921`	HARTING	cern_harting_09_02_164_2921
09 02 264 6825 (CERN library)	`09 02 264 6825`	HARTING	cern_harting_09_02_264_6825
09 02 264 6850 (CERN library)	`09 02 264 6850`	HARTING	cern_harting_09_02_264_6850
09 03 000 6104 (CERN library)	`09 03 000 6104`	HARTING	cern_harting_09_03_000_6104
09 03 000 6110 (CERN library)	`09 03 000 6110`	HARTING	cern_harting_09_03_000_6110
09 03 000 6162 (CERN library)	`09 03 000 6162`	HARTING	cern_harting_09_03_000_6162
09 03 000 6182 (CERN library)	`09 03 000 6182`	HARTING	cern_harting_09_03_000_6182
09 03 000 6225 (CERN library)	`09 03 000 6225`	HARTING	cern_harting_09_03_000_6225
09 03 000 6262 (CERN library)	`09 03 000 6262`	HARTING	cern_harting_09_03_000_6262
09 03 000 6265 (CERN library)	`09 03 000 6265`	HARTING	cern_harting_09_03_000_6265
09 03 124 6901 (CERN library)	`09 03 124 6901`	HARTING	cern_harting_09_03_124_6901
09 03 142 6901 (CERN library)	`09 03 142 6901`	HARTING	cern_harting_09_03_142_6901
09 03 160 6901 (CERN library)	`09 03 160 6901`	HARTING	cern_harting_09_03_160_6901
09 03 164 2921 (CERN library)	`09 03 164 2921`	HARTING	cern_harting_09_03_164_2921
09 03 164 6921 (CERN library)	`09 03 164 6921`	HARTING	cern_harting_09_03_164_6921
09 03 164 6922 (CERN library)	`09 03 164 6922`	HARTING	cern_harting_09_03_164_6922
09 03 164 6951 (CERN library)	`09 03 164 6951`	HARTING	cern_harting_09_03_164_6951
09 03 178 7901 (CERN library)	`09 03 178 7901`	HARTING	cern_harting_09_03_178_7901
09 03 196 2921 (CERN library)	`09 03 196 2921`	HARTING	cern_harting_09_03_196_2921
09 03 196 6921 (CERN library)	`09 03 196 6921`	HARTING	cern_harting_09_03_196_6921
09 03 224 6805 (CERN library)	`09 03 224 6805`	HARTING	cern_harting_09_03_224_6805
09 03 224 6830 (CERN library)	`09 03 224 6830`	HARTING	cern_harting_09_03_224_6830
09 03 224 6864 (CERN library)	`09 03 224 6864`	HARTING	cern_harting_09_03_224_6864
09 03 224 6864 (CERN library)	`09 03 224 6864`	HARTING	cern_harting_09_03_224_6864_a

| [09 03 232 6825 (CERN library)](https://partreel.com/p/cer

Only the beginning is shown; read the rest in the repo

Partreel

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Compared with others in Design, images & audioi

Common questions

Alternatives

Figma Context MCP

Claude Real Video

Figma MCP Server

README from the maker

PartReel — open KiCad parts registry for humans & AI agents

Why this exists

Provenance — verify us, don't trust us

For AI agents

Repository layout

License

Credits

Parts index

connector (4330)