Partuno — DigiKey & Mouser MCP Server

io.github.JPMarhefkaPublished by GitHub account JPMarhefkav4.0.1Updated Oct 24, 2026

DigiKey and Mouser MCP server for component research, BOM analysis, and sourcing.

VerifiedSTDIODesktop onlyData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Local MCP server that lets an assistant search DigiKey and Mouser components, compare offers, analyze BOMs and run bounded account workflows.

What you can do
  • Search and inspect electronic components across DigiKey and Mouser, with normalized part numbers, units and compliance values
  • Compare exact offers at a requested quantity, including price breaks, minimum order quantities, availability and partial provider failures
  • Recommend parts against hard requirements while keeping meets, does_not_meet and unknown evidence states
  • Analyze BOMs for stock, lifecycle, compliance, pricing, tariffs, lead time and substitute candidates
  • Run bounded account and project workflows such as read-only order history, list and quote previews, receiving reconciliation and confirmed mutations
When to use it
Useful when an assistant should help with electronics sourcing: picking a part for a design, checking live price and stock across two distributors, reviewing a BOM, or comparing DigiKey and Mouser offers. It suits engineers and buyers who already hold their own distributor API credentials.
Requirements
Runs locally over stdio, typically launched with uvx from the partuno PyPI package (or pip install partuno). Needs operator-owned DigiKey credentials (DIGIKEY_CLIENT_ID, DIGIKEY_CLIENT_SECRET, optional DIGIKEY_ACCESS_TOKEN) and Mouser keys (MOUSER_SEARCH_API_KEY, optional MOUSER_ACCOUNT_API_KEY) in the MCP client's environment. Network access to the distributors is required; no shared server or credentials are provided.
Before you install
You must supply your own DigiKey and Mouser API credentials; the project provides none and no shared credential pool. Some account workflows can perform mutations where the provider supports them, so review confirmations before allowing writes. It does not submit distributor orders, but prices, stock and lead times are live data that can change. Live calls count against provider quotas and terms.

Installation

In SourceWeft

  1. Open Partuno — DigiKey & Mouser MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Partuno - DigiKey & Mouser MCP Server

[Partuno logo]

[CI] [License] [Python] [partuno MCP server]

Local-first component intelligence for MCP

Partuno is an open-source, provider-neutral, local-first Model Context Protocol (MCP) server for electronic component research, BOM analysis, sourcing comparison, and safe distributor workflows. Connect an AI assistant to your own DigiKey and Mouser credentials without shared credentials or autonomous ordering, while keeping evidence, normalized attributes, and explicit uncertainty visible.

Partuno was initially developed as a native MCP server. Native MCP is the recommended connection because it works as an app in ordinary ChatGPT conversations and exposes richer tool annotations. Existing Custom GPT Action endpoints remain available for backward compatibility, including /action-openapi.json.

Partuno does not provide a shared public server or shared distributor credentials. The Render configuration is an optional reference deployment for an operator's own single-user instance.

Start here

Use the published package (recommended)

Partuno is published on PyPI and listed in the official MCP Registry. The recommended local MCP launcher is:

bash
uvx --from partuno partuno-mcp

This downloads the current published release and runs the default local stdio transport. To pin the current release exactly, use:

bash
uvx --from 'partuno==4.0.1' partuno-mcp

MCP clients that accept a local command can use uvx with these arguments:

json
{  "command": "uvx",  "args": ["--from", "partuno", "partuno-mcp"]}

Keep your operator-owned DigiKey and Mouser credentials in the MCP client's environment. See the local deployment guide for the supported variables and the native MCP setup guide for operator-owned remote deployments. For a hosted directory listing, see Partuno on Glama.

Install with pip

If uvx is not available, install the published package into an existing Python environment:

bash
python3 -m pip install partunopartuno-mcp
Develop from source

Use a checkout only when contributing, running unreleased changes, or needing the repository's .env.example and test suite:

bash
git clone https://github.com/JPMarhefka/partuno.gitcd partunopython3 -m venv .venvsource .venv/bin/activatepython -m pip install -r requirements.txtcp .env.example .envset -asource .envset +apython -m partuno

See the local deployment guide for loopback HTTP and source-checkout details.

Self-host a remote MCP server

If your client requires a reachable HTTPS endpoint, deploy your own instance with your own provider accounts, OAuth application, signing key, rate limits, and hosting budget. Start with the Render reference deployment, or use the Docker and Azure guides. There is no shared Partuno endpoint intended for public use.

Use the existing Action compatibility surface

Custom GPT Actions are retained for existing integrations. The Action/OpenAPI surface is not the primary architecture; use native MCP for new connections. The Action setup details are documented in MCP setup.

What Partuno does

  • Searches and inspects electronic components across DigiKey and Mouser.
  • Normalizes manufacturer part numbers, units, compliance values, and common distributor-specific attribute names.
  • Compares exact component offers at a requested quantity, including price breaks, minimum order quantities, order multiples, availability, and partial provider failures.
  • Recommends components against hard requirements while preserving meets, does_not_meet, and unknown evidence states.
  • Analyzes BOMs for stock, lifecycle, compliance, pricing, tariffs, lead time, and substitute candidates.
  • Supports bounded account and project workflows such as read-only order history, list and quote previews, receiving reconciliation, and carefully confirmed mutations where the provider supports them.

See the capability reference for the current scope and the safety boundary for each workflow.

DigiKey MCP server

Partuno can run as a local-first DigiKey MCP server for component search, product research, current pricing and availability, lifecycle checks, MyLists, quotes, receiving reconciliation, and other bounded account workflows. The DigiKey MCP server guide covers setup, supported workflows, and the provider-specific safety boundaries.

Mouser MCP server

Partuno also provides a Mouser MCP server surface for catalog search, exact offer comparison, read-only order history, and preview-confirmed Cart workflows. The Mouser MCP server guide explains the separate operator-owned Mouser credentials and what the server does and does not execute.

Electronics BOM MCP server

Use Partuno as an electronics BOM MCP server to consolidate duplicate rows, resolve exact products, estimate current merchandise cost, check stock and lifecycle risk, inspect compliance and lead-time signals, and find substitutes or alternate packaging. See the electronics BOM MCP server guide for a complete read-only example and known limitations.

AI component sourcing

Partuno turns a natural-language engineering request into a traceable sourcing workflow. Recommendations preserve meets, does_not_meet, and unknown evidence states, so missing or ambiguous attributes are not silently treated as qualified requirements. The natural-language examples show the intended interaction style.

DigiKey vs Mouser comparison

For an exact comparison, Partuno matches manufacturer and MPN identity first, then compares requested-quantity pricing, minimum order quantity, order multiples, purchasable quantity, availability, and manufacturer lead time. If a provider fails or returns incomplete evidence, the result remains partial instead of inventing a winner. See the DigiKey vs Mouser comparison guide.

What Partuno does not do

  • It does not supply DigiKey or Mouser credentials.
  • It does not create a shared multi-tenant credential pool.
  • It does not silently turn unknown product data into a pass.
  • It does not submit distributor orders.
  • It does not bypass provider quotas, terms, authentication, or rate limits.

See it in action

Featured example: choose a component for a 3.3 V design

Once Partuno is connected, a user can simply ask:

text
I’m choosing a dual op amp for a 3.3 V circuit. Find a few LM358-familyoptions that can operate at 3.3 V, are RoHS compliant, normally stocked, andavailable in a quantity of 10. Show the evidence behind each recommendationand keep uncertain data clearly marked.

Partuno turns that plain-language request into a provider-aware result with qualified, unverified, and rejected candidates; normalized voltage and compliance evidence; cross-distributor availability; quantity pricing; and a Pareto shortlist. It does not silently treat missing specifications as a pass.

[Partuno turning a plain-language component request into an evidence-backed recommendation]

This is a roughly 10-second prompt-to-result capture that shows the request and a smooth response scroll. Prices, stock, and lead times are live provider data and can change.

See more natural-language examples for comparison, product research, BOM review, and safe account-preview workflows.

Documentation

TopicGuide
Capabilities and safety boundariesCapability reference
Native MCP connectionMCP setup
Local stdio or loopback HTTPLocal deployment
Docker deploymentDocker deployment
Operator-owned Render deploymentRender reference
Azure deploymentAzure deployment
Security and credential handlingSecurity guide
Offline and live validationTesting guide and validation notes
Natural-language usage examplesExamples
DigiKey, Mouser, and BOM entry pointsSearch-focused guides
ContributingCONTRIBUTING.md
Security reportsSECURITY.md
Release historyCHANGELOG.md

Logo assets

The full-resolution Partuno logo is available for project pages, client listings, and integration documentation. A compact plugin icon is also included for client or plugin upload fields with strict PNG size limits.

The compact icon is intentionally optimized for small upload limits. If a host accepts larger assets, use the full-resolution logo instead. The compact icon can also be downloaded directly from the repository's raw asset URL.

When using the logo in a ChatGPT app, MCP client, or other plugin integration, identify the integration as Partuno and do not imply endorsement by DigiKey, Mouser, or another provider. Check the host platform's current dimensions, format, and file-size requirements before uploading.

Deployment and credential model

ModeBest forCredential ownership
Local stdioDesktop MCP clients and personal developmentOperator's local environment
Loopback HTTPClients that cannot launch stdioOperator's local environment
Remote HTTPSA self-hosted ChatGPT/Codex connectionOperator's own deployment and accounts

Remote mode adds OAuth and HTTPS because a hosted MCP endpoint must authenticate the client and protect upstream access. It is optional; local mode remains the default and does not require Partuno OAuth.

Project status

Partuno 4.0.1 is an active open-source release. The test suite covers offline provider contracts, MCP tool behavior, REST compatibility, credential safety, normalization, and the multi-distributor workflows. Live provider calls are opt-in because they require operator credentials and are subject to provider quotas.

See testing before running live smoke tests.

License and independence

Partuno is released under the Apache License 2.0. See NOTICE for project attribution and independence statements. Partuno is not affiliated with, endorsed by, or sponsored by DigiKey, Mouser, or any manufacturer or distributor named in the project. Their names and marks identify integrations only.

Source: README.md at commit 369d39f

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v4.0.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts