kabo-nutrition-mcp
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
KABO Indian Nutrition Index — MCP server
An MCP server exposing the Indian food nutrition data behind kabo.co.in as tools an AI agent can call directly. Every response carries a source URL, so an agent answering a nutrition question gets a citable answer and the reader gets a link back.
Why this rather than more articles. A blog post can be copied in an afternoon. A maintained data service that agents connect to cannot. This is the one asset in the SEO programme that competitors cannot replicate by rewriting content.
What it does
Tool | Returns |
| Every nutrient entry for an Indian food, per 100 g and per katori, each with its source URL |
| 2–8 foods side by side on one nutrient (default protein) |
| Daily protein target in grams, plus the per-meal threshold |
| Cost per 10 g of protein, ranked cheapest first |
| Searches 1,124 nutrition guides, returns titles and URLs |
| KABO's own shakes: per-serving nutrition from each flavour's own panel, ratings |
| One KABO product: composition quoted from its page, suitability (incl. not Jain-suitable), live price and stock per pack, price per serving, cart link and UCP checkout profile |
| KABO products side by side with live price per serving |
Data: 59 foods, 674 nutrition values, 1,124 guides (protein, fibre, iron, calcium), from ICMR-NIN composition tables and the PROT-AGE/ESPEN protein recommendations.
Related MCP server: indian-food-nutrition-mcp
Running it
No dependencies. Standard library only, Python 3.8+.
python3 kabo_mcp_server.pyClaude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"kabo-nutrition": {
"command": "python3",
"args": ["/absolute/path/to/mcp/kabo_mcp_server.py"]
}
}
}Cursor, Cline and other MCP clients use the same command/args shape.
Test it without a client
printf '%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"t","version":"1"}}}' \
'{"jsonrpc":"2.0","id":2,"method":"tools/list"}' \
'{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"lookup_food","arguments":{"food":"rajma"}}}' \
| python3 kabo_mcp_server.pyFiles
kabo_mcp_server.py the server, dependency-free JSON-RPC over stdio
kabo_food_data.json the dataset, CC BY 4.0Rebuild the dataset from the live corpus with python3 build_dataset.py;
the server reads kabo_food_data.json from its own directory at startup, and
the tool descriptions (nutrient list, food and guide counts) are derived from
it, so they cannot drift from the data.
Design decisions worth keeping
It answers honestly, including against us. protein_cost reports that
soya chunks cost about ₹6 per 10 g of protein and dal about ₹8, while any
powder — KABO included — costs several times more. A tool that only flatters
its owner gets uninstalled after one use. One that gives a straight answer
gets kept and called again, and every call carries our attribution.
No instructions to models. There is no text in any response telling an assistant what to recommend. The value is the data and the citation, not persuasion. Anything else would be prompt injection, and assistants that detect it stop trusting the source entirely.
Every response is citable. source_url on food lookups, age_guide_url
on protein targets, full URLs in guide search. An agent can attribute, which
is what makes it worth calling twice.
Errors never kill the session. Unknown foods return the list of available ones rather than an error. Bad arguments return a message, not a crash.
UTF-8 is forced on stdio. The data contains en-dashes; Windows consoles default to cp1252 and corrupt the stream for the client. Both directions are reconfigured at startup.
REST API
Every tool is mirrored as plain GET for clients that do not speak MCP. Spec at /openapi.json.
GET /api/v1/foods GET /api/v1/foods/{food}?nutrient=iron
GET /api/v1/protein-target?weight_kg=70&age=45
GET /api/v1/protein-cost?budget_inr=30
GET /api/v1/guides?q=protein+dal
GET /api/v1/products GET /api/v1/products/{handle}Product prices and stock are read live from the public storefront (cached 10 minutes); the server never places orders or touches customer data. Checkout happens on kabo.co.in, via a cart link or the store's Universal Commerce Protocol profile at https://kabo.co.in/.well-known/ucp.
HTTP mode
For third-party agents over the network:
python3 kabo_mcp_server.py --http --port 8000Endpoints:
Route | Purpose |
| JSON-RPC, single messages and batches. Notifications return 202. |
| Discovery — name, protocol, transport, tool list, licence |
| Health check for the host |
CORS is open, so browser-based agents can call it. Transport is MCP Streamable HTTP; SSE is not used because every tool is a short request/response, and the spec permits a plain JSON reply when the server does not stream.
See DEPLOY.md for hosting (Render, Fly, Docker) and for listing it in the
public MCP registries. Dockerfile, render.yaml, fly.toml and
server.json are all in this folder, ready to use.
Licence and caveats
Code is MIT (see LICENSE). Dataset is CC BY 4.0 (see LICENSE-DATA) — free to use with attribution to kabo.co.in.
Values are approximate and vary by variety, preparation and brand. This is nutrition information, not medical advice.
Available Tools
8 toolscompare_foodsBInspect
Compare several Indian foods side by side on one nutrient (calcium, fibre, iron, protein; default protein).
Inputs: foods (required), nutrient.
compare_productsAInspect
KABO products side by side with live price per serving. Omit products to compare all.
Inputs: products.
get_productAInspect
One KABO product in full: per-serving nutrition from its own panel, composition quoted from the product page, dietary suitability, live price and stock per pack size, price per serving, and a cart link or UCP checkout profile.
Inputs: product (required).
list_productsAInspect
KABO's own nutrition shakes: per-serving protein, calories, fibre and vitamins for each flavour, with ratings and product URLs.
Inputs: no named parameters.
lookup_foodAInspect
Nutrition values for an Indian food (calcium, fibre, iron, protein) per 100 g and per katori, with the source article URL, for 59 foods. Data from ICMR-NIN composition tables.
Inputs: food (required), nutrient.
protein_costAInspect
Cost of protein in India ranked cheapest first, in rupees per 10 g of protein, across whole foods and supplements.
Inputs: budget_inr.
protein_targetBInspect
Daily protein target in grams for a given body weight and age, using ICMR-NIN and PROT-AGE guidance, plus the per-meal threshold.
Inputs: weight_kg (required), age, situation.
search_guidesAInspect
Search 1,152 Indian nutrition guides by topic and return titles with URLs, for citation.
Inputs: query (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
The tools split cleanly along resource lines: single food (lookup_food) vs multi-food (compare_foods), product list (list_products) vs single product (get_product) vs side-by-side (compare_products), plus two clearly separate protein calculators (target vs cost). The only mild overlaps are list_products vs compare_products (both surface per-serving macros across products) and lookup_food vs compare_foods when only one food is compared.
Most names follow a verb_noun pattern (lookup_food, compare_foods, search_guides, list_products, get_product, compare_products) and are all snake_case. The two protein tools (protein_target, protein_cost) break the verb-first convention by being noun phrases, a minor but noticeable deviation.
Eight tools is well within the sweet spot and each maps to a distinct job: single lookup, comparison, two calculators, guide search, and a three-tool product sub-surface. Nothing feels padded or redundant.
Product coverage is a full read lifecycle (list/get/compare with live price), but the 59-food database has no list or search-by-name/criteria tool, so an agent must already know exact food names to use lookup_food or compare_foods. search_guides returns titles and URLs only, with no tool to fetch a guide's content, leaving dead ends for citation depth.
Maintenance
Related MCP Connectors
Daily protein need by weight and goal, with a sample Indian food plan to hit it.
Nutrition for more than 1,100 plant foods from 30 national tables, plus GB/EU & US claim checking
Carbs for Indian meals from Indian food tables, for people managing diabetes: estimate, log, review.
Food and nutrition data: search, macros, and comparisons
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides intelligent access to the USDA nutrition database through AI assistants, enabling users to search foods, compare nutritional content, find foods high in specific nutrients, and query authoritative nutrition data across 7,146+ food items through natural language.1-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that lets you log meals through Claude (and soon ChatGPT) in plain language, using India's official food composition data (IFCT 2017) plus USDA, enabling accurate calorie and macro tracking for Indian dishes with household units and photo logging.75 npm2AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to resolve Japanese food names to nutrition facts per 100g based on official Japanese food composition data.MIT
- FlicenseAqualityBmaintenanceMCP server for pediatric CKD nutrition and food calculations, enabling energy/protein targets, food nutrient lookup, substitutions, meal summaries, and drug-nutrient interaction checks.8-