Open Food Facts MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OFF_USER_AGENT | Yes | An application name and version followed by a monitored contact email (e.g. 'open-food-facts-mcp/0.1.0 (you@example.org)'). Open Food Facts requires a descriptive User-Agent that identifies the application and provides contact information. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_productB | Read one Open Food Facts product by barcode. Nutrition and allergen data are informational. |
| search_productsC | Search Open Food Facts products with documented taxonomy filters. |
| search_textC | Full text product search via Search-a-licious. |
| get_taxonomyC | Autocomplete an Open Food Facts taxonomy. |
| compare_productsB | Compare 2–5 products only when normalized nutrition basis and preparation match. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
search_products (taxonomy filters) and search_text (full-text) overlap in that both search products, but the descriptions clearly delineate structured vs. free-text search; the other tools are distinct.
All tools use snake_case with a verb_noun structure (get_, search_, compare_), consistent throughout.
Five tools for a read-only product database API is well-scoped; each tool covers a distinct operation and none feel redundant.
The surface covers lookup, structured search, full-text search, taxonomy autocomplete, and comparison, which meets core read-only needs. Minor gaps might include batch retrieval or more taxonomy exploration, but no dead ends for typical queries.