openfoodfacts-mcp-server
Server Details
Barcode lookup, nutrition search, and product comparison for 3M+ crowd-sourced food products.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.5/5 across 4 of 4 tools scored.
Each tool has a clear, distinct purpose: browsing taxonomy for filter IDs, searching products, getting full product details, and comparing multiple products. There is no ambiguity between them.
All tool names follow the consistent verb_noun pattern with prefix 'off_': browse_taxonomy, compare_products, get_product, search_products. No naming conflicts or inconsistencies.
4 tools is well-scoped for a read-only food facts server, covering search, detail retrieval, comparison, and taxonomy browsing without unnecessary overlap or bloat.
The toolset covers the full read lifecycle: browse taxonomy to find filters, search with filters, get full product details, and compare multiple products. No obvious gaps for a read-only data access server.
Available Tools
4 toolsoff_browse_taxonomyBrowse Food Facts TaxonomyARead-onlyIdempotentInspect
Browse and search the canonical tag vocabulary for Open Food Facts filter facets. Returns tag IDs and display names for use as filter values in off_search_products. Covers categories, labels/certifications, allergens, additives, countries, NOVA groups, and Nutri-Score grades. The taxonomy is embedded — not fetched live — because the OFF taxonomy API is unavailable to anonymous bot clients. Tag IDs use the "en:" prefix convention (e.g. "en:organic", "en:gluten-free", "en:milk"). Always use these tag IDs as filter values, not plain English terms.
| Name | Required | Description | Default |
|---|---|---|---|
| facet | Yes | "categories" covers food categories (en:cheeses, en:breakfast-cereals). "labels" covers certifications (en:organic, en:fair-trade). "allergens" covers declared allergens (en:milk, en:gluten). "additives" covers E-numbers (en:e322). "countries" covers country-of-sale tags (en:france). "nova_groups" and "nutrition_grades" return the complete fixed vocabularies. | |
| limit | No | Maximum entries to return (1–100, default 20). Categories has many entries — always provide a search term when browsing categories. | |
| search | No | Case-insensitive substring filter against tag ID or display name. Example: "gluten" returns en:gluten, en:no-gluten. Omit to list all entries for the facet (may be large for categories). |
Output Schema
| Name | Required | Description |
|---|---|---|
| cap | No | The limit that was applied. |
| tags | Yes | Matching tag entries. |
| facet | Yes | The facet name that was queried (echoes the input). |
| shown | No | Number of tags returned. |
| truncated | No | True when more tags exist beyond the limit. |
| total_in_facet | No | Total entries in this facet before search filtering. Large for categories. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the taxonomy is embedded (not fetched live) due to API unavailability for anonymous bot clients, adding meaningful behavioral context beyond annotations. Annotations already declare readOnlyHint and idempotentHint, and the description explains why the data is static.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with no wasted words. It front-loads the purpose and usage, then adds necessary details. The entire description is just a few sentences, efficiently conveying all key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema, the description adequately covers the return content (tag IDs and display names), the embedded nature, and the prefix convention. It could mention that the output is a list of objects, but that is likely in the output schema. Overall, it is complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema coverage, baseline is 3. The description adds value by explaining the 'en:' prefix convention, advising to provide a search term for categories due to large size, and giving specific examples. This enriches the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool browses and searches the canonical tag vocabulary for Open Food Facts filter facets, returning tag IDs and display names for use as filter values. It implicitly distinguishes from sibling tools like off_search_products by specifying its purpose is taxonomy retrieval for filters.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use the tool (get tag IDs for off_search_products) and provides instructions to always use tag IDs not plain English terms. It does not explicitly list when not to use, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
off_compare_productsCompare Food Products Side-by-SideARead-onlyIdempotentInspect
Side-by-side nutrition and scoring comparison for 2–10 products by barcode. Fetches all products in parallel and returns a normalized table of energy (kcal/100g), fat, saturated fat, sugars, salt, protein, fiber, Nutri-Score, NOVA group, and Green-Score. Designed for "which of these cereals is healthiest?" or "compare these pasta brands" workflows. Missing nutrition data for any product is preserved as absent — comparisons are not imputed. Scores carry regional formula caveats. Data under ODbL 1.0 — cite Open Food Facts in downstream use.
| Name | Required | Description | Default |
|---|---|---|---|
| barcodes | Yes | 2–10 barcodes to compare. All products are fetched in parallel. Example: ["3017620422003", "7622210100146"]. |
Output Schema
| Name | Required | Description |
|---|---|---|
| products | Yes | Comparison rows, one per barcode in input order. |
| not_found | Yes | Barcodes with no contributor record. Not an error — the product may exist but not yet entered in Open Food Facts. |
| succeeded | Yes | Number of barcodes that resolved to a found product. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds value by noting parallel fetching, normalized table output, data licensing, and the handling of missing nutrition data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences plus a licensing note, all front-loaded with the main action. Every sentence contributes meaningful information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the single parameter, comprehensive annotations, and existing output schema, the description covers the tool's behavior, limitations, and licensing adequately. No major gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 100% coverage with a clear description. The description adds context: 'All products are fetched in parallel' and provides an example, going beyond the schema's details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Side-by-side nutrition and scoring comparison for 2–10 products by barcode.' It uses a specific verb ('compare') and resource ('food products') and distinguishes itself from siblings like off_get_product (single product) and off_search_products (search).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit use cases like 'which of these cereals is healthiest?' and 'compare these pasta brands workflows.' It covers data handling (missing data preserved, regional caveats) but does not explicitly state when not to use the tool or mention alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
off_get_productGet Food Product by BarcodeARead-onlyIdempotentInspect
Fetch a packaged food product by barcode (EAN-13 or UPC) from Open Food Facts. Returns the product name, brand, quantity, ingredients (raw text and parsed list), allergens, additives, computed scores (Nutri-Score a–e, NOVA 1–4, Green-Score), nutrition per 100g and per serving, categories, labels, packaging, origins, image URL, and data completeness. Open Food Facts is a crowd-sourced database — a missing field means "not yet entered by contributors," not that the attribute is absent from the actual product. Computed scores carry regional formula caveats and are indicators, not absolute rankings. Data is under ODbL 1.0 — cite Open Food Facts in downstream use.
| Name | Required | Description | Default |
|---|---|---|---|
| fields | No | Subset of fields to return. Omitting returns all standard fields. Use to reduce payload when only scores or ingredients are needed. | |
| barcode | Yes | EAN-13 or UPC barcode (8–14 digits). The primary key for Open Food Facts. Example: "3017620422003" (Nutella FR). |
Output Schema
| Name | Required | Description |
|---|---|---|
| found | Yes | False when the barcode exists in no contributor record (status:0). A false result means no contributor has entered this product yet — not that the product does not exist. |
| barcode | Yes | Barcode as returned by the API. |
| product | No | Product data. Absent when found is false. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly, openWorld, and idempotent hints. The description adds crucial context: missing fields are due to crowd-sourced gaps (not product absence), computed scores have regional caveats, and data is under ODbL 1.0. This goes beyond annotations to manage expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core action and progressively adds detail. It is informative without being overly verbose, though slightly longer than minimal. Each sentence serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool complexity (multiple returned fields, crowd-sourced data, computed scores) and the presence of an output schema (not shown but implied), the description covers all necessary context: what is returned, caveats, licensing, and parameter usage. It is sufficiently complete for reliable invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds an example barcode and clarifies the fields parameter reduces payload. It also explains the barcode pattern is a primary key. This adds meaningful context beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches a packaged food product by barcode from Open Food Facts, listing many specific return fields. It is distinct from sibling tools (browse taxonomy, compare, search) which focus on different operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when a barcode is available, but does not explicitly contrast with siblings (e.g., 'Use off_search_products when querying by name'). It provides guidance on interpreting missing fields but no when-not-to-use or alternative recommendations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
off_search_productsSearch Food ProductsARead-onlyIdempotentInspect
Search Open Food Facts by text query or structured tag filters. Returns a summary list with barcodes, product names, brands, Nutri-Score, NOVA group, and categories — enough for triage and selection, not full label data. Use off_get_product on the returned barcodes for complete details. Text query and tag filters are mutually exclusive routing paths: when query is provided, a text search is performed and tag filters are ignored; when only tag filters are provided (no query), structured facet filtering is applied. Tag filter values must be canonical tag IDs (e.g. "en:organic", "en:gluten-free") — use off_browse_taxonomy to resolve human terms to tag IDs. At least one search parameter is required. Data is crowd-sourced; result count reflects contributed products, not all products in the market. Data under ODbL 1.0 — cite Open Food Facts in downstream use.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (1-based). Use with page_size to paginate results. | |
| query | No | Full-text search term across product names, brands, and ingredients. When provided, routes to the text search engine — tag filters (categories_tag, brands_tag, etc.) are ignored in this path. Example: "dark chocolate 70%". | |
| sort_by | No | Sort order for tag-filter results. "unique_scans_n" surfaces the most-scanned products. Ignored on text-query searches (search.openfoodfacts.org does not support server-side sort). Omitting returns results in default database order. | |
| page_size | No | Results per page (1–50, default 20). Keep low for initial exploration; increase for comparison workflows. | |
| brands_tag | No | Brand slug (lowercased, hyphenated). Example: "nutella", "kelloggs". Fuzzy — partial matches may work. | |
| labels_tag | No | Canonical label/certification tag ID. Example: "en:organic", "en:fair-trade", "en:no-gluten". Use off_browse_taxonomy with facet="labels". | |
| nova_group | No | Filter by NOVA food processing class. "1"=unprocessed/minimally processed, "4"=ultra-processed. Products without a NOVA score are excluded. | |
| countries_tag | No | Canonical country tag ID. Example: "en:france", "en:united-states". Filters to products sold in that country. | |
| categories_tag | No | Canonical category tag ID. Example: "en:breakfast-cereals", "en:cheeses". Use off_browse_taxonomy with facet="categories" to discover valid values. | |
| nutrition_grade | No | Filter by Nutri-Score grade. "a" is highest nutritional quality, "e" is lowest. Products without a score are excluded. |
Output Schema
| Name | Required | Description |
|---|---|---|
| cap | No | The page_size that was applied. |
| page | Yes | Current page number (1-based). |
| shown | No | Number of products returned on this page. |
| total | Yes | Total matching products in the database for this query. |
| notice | No | Guidance when results are empty — echoes filters and suggests how to broaden. |
| products | Yes | Matching products. Use barcodes with off_get_product for full label data. |
| truncated | No | True when more results exist beyond this page. |
| page_count | Yes | Products returned on this page (mirrors page_size except on the last page). Not the total number of pages. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds important behavioral context beyond annotations: data is crowd-sourced with result counts reflecting only contributed products, text and tag filter routes are mutually exclusive, and sort_by is ignored on text queries. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: purpose, return summary, usage flow, parameter behavior, data caveats, and licensing. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity with 10 parameters and mutual exclusivity, the description covers all necessary aspects: purpose, usage, parameter semantics, behavioral notes, and data quality. The presence of an output schema makes the omission of return details appropriate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds critical semantics: the mutual exclusivity of query and tag filters, that tag filters are ignored when query is provided, and guidance on using off_browse_taxonomy for canonical tag IDs. This goes well beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: search Open Food Facts by text query or tag filters. It distinguishes itself from siblings by referencing off_get_product for full details and off_browse_taxonomy for tag resolution, making the scope unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit guidance is given on when to use this tool vs alternatives: use off_get_product for complete details, off_browse_taxonomy for tag IDs. The mutual exclusivity of query and tag filters is clearly explained, along with the requirement for at least one search parameter.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!