seed-oil-tracker-mcp
Seed Oil Tracker MCP Server
A free, hosted MCP server that gives AI assistants live access to the largest restaurant seed oil database: 500+ US chains, 40,000+ menu items, each with an estimated PUFA (polyunsaturated fat) value built from published nutrition data and disclosed cooking oils.
Ask your assistant things like:
Does Chick-fil-A use seed oils?
What oil does Chipotle cook with?
What is the cleanest thing to order at Five Guys?
Which chains have the lowest seed oil overall?
Connect
No key, no account, read only.
Endpoint (streamable HTTP):
https://seedoiltracker.com/mcpClaude (claude.ai): Settings, then Connectors, then Add custom connector, then paste the endpoint URL.
Claude Code:
claude mcp add --transport http seed-oil-tracker https://seedoiltracker.com/mcpAny other MCP client: streamable HTTP transport, no auth.
Setup guide: https://seedoiltracker.com/mcp-setup
Related MCP server: eatwise-mcp
Run locally (stdio)
Prefer a local process, or your client only speaks stdio? This repo ships a
zero-dependency stdio server (server.py, Python 3.8+, standard library
only). It answers the MCP handshake locally and forwards tool calls to the
hosted endpoint.
python server.pyClaude Desktop config example:
{
"mcpServers": {
"seed-oil-tracker": {
"command": "python",
"args": ["/path/to/server.py"]
}
}
}Or with Docker:
docker build -t seed-oil-tracker-mcp .
docker run -i seed-oil-tracker-mcpTools
Tool | What it does |
| One chain's seed oil letter grade, the oil it fries in, the cleanest menu items to order, and the highest to avoid. Fuzzy name matching. |
| Find covered chains by full or partial name. |
| Chains ranked cleanest first or worst first by average seed oil per menu item. |
Data
Same dataset that powers the Seed Oil Tracker iOS app and seedoiltracker.com. Also available as a no-key JSON API and ChatGPT Action (https://seedoiltracker.com/ai-tool) and as an open dataset in CSV and JSON, licensed CC BY 4.0 (https://seedoiltracker.com/open-data).
Methodology and citation: https://seedoiltracker.com/methodology
About
Built by Seed Oil Tracker (https://seedoiltracker.com). The hosted server is the primary way to connect; this repository documents it and ships the local stdio bridge. Questions and issues welcome here.
Available Tools
3 toolsget_chainA chain's seed-oil grade, frying oil, and cleanest ordersA
Look up one US restaurant chain: its seed-oil letter grade, the oil it cooks with, the lowest-seed-oil menu items to order, and the highest to avoid. Fuzzy name matching ('chickfila' finds Chick-fil-A).
Inputs: name (required).
get_rankingsCleanest or worst chains, rankedA
Ranked list of chains by average seed oil per menu item. order=best (cleanest first) or worst.
Inputs: limit, order.
search_chainsFind matching chain namesA
Search the 500+ covered US chains by (partial) name; returns matches with grades.
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: single chain lookup, ranking list, and name search. No overlap in functionality.
All tools follow a consistent verb_noun snake_case pattern (get_chain, get_rankings, search_chains).
Three tools is well-scoped for a focused domain of tracking seed oils in chains, providing lookup, rankings, and search without redundancy.
Core operations are covered: individual lookup, ranked comparisons, and search. A potential minor gap is lack of a tool to list all chains, but search with partial name covers most use cases.
Related MCP Connectors
Nutrition facts for 24,000+ menu items of 100+ Japanese restaurant chains (kcal, PFC, salt, vitamins), each with the chain's source document. Search items, total a meal, and request missing chains.
USDA FoodData Central nutrient lookup, FDA recall watch, EU FMCG labelling via remote MCP
Food and nutrition data: search, macros, and comparisons
AI-native restaurant discovery: verified/menu-indexed/discovered tiers + signed allergy-safety data.
Related MCP Servers
- AlicenseAqualityCmaintenanceProduct evaluation MCP server for US packaged food. Health scores, ingredient safety, regulatory flags, recall history, corporate ownership.21MIT
- AlicenseNot gradedqualityCmaintenanceProvides a local-first Chinese dietary coaching server that reviews meals, recomputes nutrition from bundled food data, and manages user profiles and meal history in a private local SQLite database.MIT
- AlicenseNot gradedqualityBmaintenanceEnables a chat assistant to log what you ate — text, voice notes, recipe portions, or label/plate photos — by resolving foods against the Bundeslebensmittelschlüssel, Open Food Facts, or Tandoor recipe nutrition and storing copy-on-write nutrient entries in a local SQLite log. It serves these tools over stateless streamable HTTP MCP, grouping entries into meals and summarizing days, weeks, and training/body-weight data when an OpenGym endpoint is configured.GPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables querying national weighted estimates of consumer-product-related emergency-department injuries in the US, including per-product yearly figures with small-sample instability flags, rankings of the products injuring people most, and keyword lookup of product/activity codes. Runs keyless over HTTP or as a local stdio server, requiring no credentials.304 npmMIT