Mouser Electronics Search

Created By
cmaurer14 days ago
Exposes the Mouser Search API as MCP tools so MCP-aware clients (Claude Code, Claude Desktop, etc.) can query Mouser's parts catalog.
Overview

mouser-search-mcp

Model Context Protocol server for the Mouser Electronics Search API.

Exposes the Mouser Search API as MCP tools so MCP-aware clients (Claude Code, Claude Desktop, etc.) can query Mouser's parts catalog.

Tools

ToolEndpointWhat it does
search_by_keywordPOST /api/v1/search/keywordKeyword search across the catalog (up to 50 parts). Supports paging and RoHS/in-stock filters.
search_by_part_numberPOST /api/v1/search/partnumberLook up 1–10 part numbers (pipe-separated), with optional exact-match.
search_by_keyword_and_manufacturerPOST /api/v2/search/keywordandmanufacturerKeyword search scoped to one manufacturer by name.
search_by_part_number_and_manufacturerPOST /api/v2/search/partnumberandmanufacturerPart-number lookup scoped to one manufacturer by name.
list_manufacturersGET /api/v2/search/manufacturerlistEnumerate manufacturer names (use the result to populate the manufacturer_name argument on the two manufacturer-filtered tools).

Prerequisites

Install

Using uv (recommended):

uv pip install -e .

Or with pip:

pip install -e .

Configure

The server reads the API key from the MOUSER_API_KEY environment variable. Copy .env.example to .env and fill in your key, or export it in your shell.

Run

The server speaks MCP over stdio:

MOUSER_API_KEY=... mouser-search-mcp

Use with Claude Code

Register the server (replace the path and key):

claude mcp add mouser-search \
  --env MOUSER_API_KEY=your-key \
  -- mouser-search-mcp

Use with Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mouser-search": {
      "command": "mouser-search-mcp",
      "env": {
        "MOUSER_API_KEY": "your-key"
      }
    }
  }
}

If mouser-search-mcp is not on your PATH, point command at the absolute path to the script (e.g. inside your venv's bin/).

Notes

  • Mouser returns at most 50 records per search response. Use records + starting_record (v1 keyword search) or records + page_number (v2 keyword+manufacturer search) to page.
  • search_options accepts None, Rohs, InStock, or RohsAndInStock — only one at a time.
  • part_search_options accepts None or Exact.
  • The cart and order endpoints documented by Mouser require an Ordering API key and are not exposed by this server — it covers search only.

Releasing

Versioning and releases are fully automated by python-semantic-release. Every push to main runs .github/workflows/release.yml, which:

  1. Inspects commits since the last tag.
  2. Decides the next version (or does nothing if no release-worthy commits).
  3. Updates version in pyproject.toml, generates the changelog, commits, and pushes a vX.Y.Z tag.
  4. Builds wheel + sdist and uploads them to PyPI.
  5. Creates a GitHub Release with auto-generated notes.

Commit grammar

Commits must follow Conventional Commits. The leading keyword decides the bump:

PrefixBumpExample
feat:minorfeat: add list_manufacturers tool
fix:patchfix: handle empty Errors array
perf:patchperf: reuse httpx client
feat!: / BREAKING CHANGE: in bodymajorfeat!: rename tools
docs:, chore:, refactor:, test:, ci:, style:none(no release cut)

Anything else is ignored. If you push a flurry of small commits, semantic-release collapses them into a single release on the next workflow run.

One-time setup

These steps need to be done once in the GitHub UI before the workflow can publish:

  1. PyPI account + token — create a PyPI account, then on the API tokens page generate an account-scoped token (the project doesn't exist on PyPI yet, so it can't be project-scoped on the first release; re-scope it to mouser-search-mcp after the first successful publish).
  2. Repo secret — in GitHub: Settings → Secrets and variables → Actions → New repository secret, name PYPI_API_TOKEN, paste the token value.
  3. Workflow permissionsSettings → Actions → General → Workflow permissions must be set to Read and write permissions so semantic-release can push the version bump commit and tag.

After that, just merge to main with a feat: or fix: commit and the rest happens automatically. To skip a release, use a non-bumping prefix (docs:, chore:, etc.) or include [skip ci] in the commit message.

Server Config

{
  "mcpServers": {
    "mouser-search": {
      "command": "mouser-search-mcp",
      "env": {
        "MOUSER_API_KEY": "your-key"
      }
    }
  }
}
Project Info
Created At
14 days ago
Updated At
16 hours ago
Author Name
cmaurer
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago