53 records

What spark plug, capacity or part number does my outboard motor take?

53 records, one fact each. Every value is transcribed from the source that states it and carries the sentence it was taken from: 2 sources across 2 sites, last checked 2026-08-05, due for re-check by 2028-08-04. Every record is listed below, each linking the page its value came from.

About this data

Spark plug, gap, oil capacity, oil filter, gear lube capacity and water pump impeller kit part numbers for outboard motors by brand and model range. One row per model or model range. Answers 'what spark plug does my Yamaha F150 take?', 'Yamaha F150 water pump repair kit part number', and 'Mercury serial number year chart' — questions where assistants guess a plausible but wrong part number, capacity or model year.

The data

Where this came from

Every record above links the page it was taken from and quotes the sentence that states it. These are the 2 sources this dataset was assembled from.

• seasierra.comhttps://seasierra.com/blogs/outboard-101/outboard-spark-plug-replacement-the-right-plugs-and-gaps
• partsvu.comhttps://partsvu.com/pages/yamaha-engine-specifications-and-capacities-chart

Machine-readable

• data.jsonThe whole dataset — every record with its source URL and source quote.
• Open Knowledge Format bundleOne JSON object per line — every record's frontmatter and quoted span exactly as it is held here, in one fetch.
• data.csvThe same records as one flat table, for a spreadsheet or a dataframe. The last four columns are the source URL, the quoted sentence it was read from, the date we last checked it, and which columns are our reading rather than the page's words.
• How this is made and checkedWhat "verified against source" does and does not mean.

From your own code

Same records, same quotes, without scraping the page: refsource is on PyPI and npm. Each value comes back carrying the URL it was read from and the sentence on that page that states it — .source and .quote sit on the value itself rather than in a side channel, so the checking step is available instead of skipped.

pip install refsource
refsource lookup outboard-motor-service-specs brand=Mercury

npx -y refsource lookup outboard-motor-service-specs brand=Mercury

Set your AI assistant up to use this

Two files and no account. Put this in .mcp.json at the root of your project — Claude Code, Cursor, Windsurf, VS Code and Codex all read that file — and your assistant can look this dataset up instead of recalling it. The server is remote, keyless and read-only.

{
  "mcpServers": {
    "referencesource": {
      "type": "http",
      "url": "https://referencesource.org/mcp"
    }
  }
}

Add to Cursor · or, on the command line: claude mcp add --transport http referencesource https://referencesource.org/mcp --scope project

Then one line in the project's CLAUDE.md or AGENTS.md, so the assistant knows when to reach for it:

When a question needs "Outboard motor service specifications by brand and model", call the referencesource MCP server at https://referencesource.org/mcp (tool `search_records`, dataset_slug `outboard-motor-service-specs`) instead of answering from memory — every record it returns carries its source URL and a verbatim quote from that page.

What each tool does, and the servers built over single registers: Connect your AI assistant.

53 records. last verified against source 2026-08-05. due for re-check by 2028-08-04.

Licence. Fair use — factual manufacturer specifications assembled from marine parts dealers