SKS Nutrition AI

Find ingredient suppliers

find_ingredient_suppliers

Read-onlyIdempotent

Find who supplies a food, beverage, dietary-supplement or pet-food ingredient: manufacturers, distributors and traders from the SKS Ingredient Index (about 265 ingredients, 790 suppliers worldwide, compiled from public sources). Use it whenever the user asks who makes, sells, sources or distributes an ingredient, wants supplier or vendor options, or is choosing where to buy a raw material (e.g. 'allulose suppliers', 'Halal collagen manufacturers', 'US-based ashwagandha suppliers', 'who sells MCT oil powder'). Filter by country and by claimed credential (Halal, Kosher, Organic, Non-GMO, GFSI food safety, GMP). Returns supplier name, country, type, website, listed products and claimed credentials, plus the ingredient's FDA GRAS notice count, US private-label retailer status and a link to the full page. Credentials are suppliers' own claims; suppliers are alphabetical, not ranked.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ingredient": "<ingredient>"
    },
    "name": "find_ingredient_suppliers"
  }
}

Input Schema

Name	Required	Description
`limit`	No
`country`	No	Optional supplier headquarters country, e.g. 'United States', 'China', 'India', 'Germany'.
`credential`	No	Optional claimed credential to require.
`ingredient`	Yes	Ingredient name, trade name or form, e.g. 'allulose', 'vitamin D3', 'KSM-66', 'pea protein isolate'.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the description's added context is what counts. It discloses data provenance ("compiled from public sources"), an ordering caveat ("suppliers are alphabetical, not ranked"), and a trust caveat ("Credentials are suppliers' own claims") — exactly the behavioral facts an agent needs to interpret results honestly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, front-loaded with purpose and corpus scope before the usage triggers and output description. The parenthetical statistics and example list are dense but each carries selection or interpretation value; the sentence is long enough to be slightly heavy for a single read.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by enumerating returned fields (supplier name, country, type, website, listed products, credentials, plus FDA GRAS notice count, private-label status and page link). Combined with the corpus size and ranking caveat, an agent has everything needed to call and interpret it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

At 75% schema coverage the baseline is 3, but the description adds real meaning: it explains that filtering is available by country and by claimed credential and enumerates the credential families in prose, plus shows how filters combine in examples like "US-based ashwagandha suppliers". It says nothing about the `limit` parameter (default 25, max 50), which is the one remaining gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Find who supplies a food, beverage, dietary-supplement or pet-food ingredient: manufacturers, distributors and traders") and immediately scopes the corpus ("SKS Ingredient Index, about 265 ingredients, 790 suppliers"). This clearly separates it from siblings like get_ingredient_profile and search_gras_notices without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit use triggers ("whenever the user asks who makes, sells, sources or distributes an ingredient... or is choosing where to buy a raw material") backed by four concrete query examples. It never names a sibling to use instead or states when-not-to-use, so it falls short of full alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SKS Nutrition AI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?