Foodbe

io.github.bleemohrPublished by GitHub account bleemohrv3.1.0Updated Nov 5, 2026

Food list analyzer and cited food answers for agents. Also recipes, meal plans and grocery lists.

Overview

AI-generated overview

Foodbe gives an assistant cited food-science answers, ingredient profiles, recipe and meal-plan generation, grocery lists and grocery-cart analysis.

What you can do
  • Look up food questions in a curated fact library, with a headline answer and sources, or with three expert views
  • Get structured ingredient profiles: category, allergens, swaps, storage, price and carbon footprint
  • Analyze a grocery list, cart, menu or recipe of up to 50 ingredients for health, taste and cost
  • Find recipes for a dish filtered by diet and allergies
  • Build 1- to 7-day meal plans within an optional dollar budget
  • Generate grocery lists with per-item costs and a total, and send feedback on missing or weak answers
When to use it
Useful when an assistant answers cooking, ingredient-substitution, food-culture or nutrition-adjacent questions and should cite sources rather than improvise, or when it plans meals, recipes and shopping lists with diet, allergy and budget constraints.
Requirements
Remote streamable HTTP endpoint; no local install. An optional x-foodbe-key header raises the free allowance of 5,000 answers per IP address; a free key with 5,000 tokens is available from the provider, and each served answer uses one token.
Before you install
The x-foodbe-key header is a secret and should be kept out of logs and shared transcripts. Answers consume tokens once the free per-IP allowance is used. Nutrition numbers are not included in ingredient profiles, and feedback messages are rate-limited per day.

Installation

In SourceWeft

  1. Open Foodbe in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.bleemohr%2Ffoodbe/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "foodbe": {
      "type": "http",
      "url": "https://foodbe-v3-production.up.railway.app/v1/mcp"
    }
  }
}

Tools

8

foodbe_query

Ask a food question

Call before you answer a question about food science, cooking technique, food culture, substitutions or ingredients. Foodbe looks the question up in its library of thousands of hand-curated, human-approved facts and returns the answer as "headline" with its sources, so you can explain the reasons behind a food choice to a human and be trusted for it. It also returns related follow-up questions when it has them. If no approved answer exists, it returns outcome "refused" with related questions that have approved answers, so you can say so instead of guessing. A limited number of calls work without a key. After that, a key is needed in the x-foodbe-key header.

Parametersquestionrequired

foodbe_query_all

Ask all three experts

Call when you need the next level of food data to better explain your food decisions. Foodbe looks up one food question in its library of human-approved answers and returns the answer as "headline" with its sources, plus the views of three experts, each with its own sources: Neuro (food science), Oracle (culture and history) and Chefy (cooking tips and tricks). An expert with nothing approved for the question is left out. Also returns related follow-up questions, when it has them. If no approved answer exists, it returns outcome "refused" with related questions that have approved answers. A limited number of calls work without a key. After that, a key is needed in the x-foodbe-key header.

Parametersquestionrequired

foodbe_ingredient

Get an ingredient profile

Call before you recommend or swap an ingredient. Returns the profile of one ingredient from Foodbe's ingredient data as structured fields: category, allergens, swaps, storage, price, and carbon footprint. Nutrition numbers are not included. Every field comes from stored data, never from a model. A limited number of calls work without a key. After that, a key is needed in the x-foodbe-key header.

Parametersnamerequired

foodbe_cart_breakdown

Analyze a food list or purchase

Foodbe's list analyzer. Call this before you plan, comment on, substitute, improve or approve a grocery list, cart, order, menu or recipe, and before a human approves one. Send up to 50 ingredient names. Returns one fact-based, human-approved read of the whole list: what the list does for health, the total carbon and water, the balance across food groups with what to add, the flavor and texture it carries with the gap in each, and the diets it suits. It also returns swaps that keep flavor and texture. It returns a cook's read in chefy_read, broken down by food. Each food comes back with its own lines: how to cook it, what to use if you run out, and what it pairs with. A closing note names the list's biggest gap and its carbon and water. Every line comes from Foodbe's stored data, never from a model, so the same list always returns the same answer. Names Foodbe does not have are listed under not_found. A limited number of calls work without a key. After that, a key is needed in the x-foodbe-key header.

Parametersitemsrequired

foodbe_recipe_finder

Find a recipe

Call this when a user asks for a recipe or for what to cook. Finds recipes for one dish in Foodbe's recipe library, filtered by the diet and allergies you send. Returns outcome "served" with a text line and recipe cards: name, image, a short fact, servings, prep time, cook time and calories. Every recipe comes from Foodbe's stored data, never from a model. If no recipe matches, it returns outcome "not_found" and costs nothing. A limited number of calls work without a key. After that, a key is needed in the x-foodbe-key header.

Parametersdietdishrequiredallergies

foodbe_meal_plan

Build a meal plan

Call this when a user asks for a meal plan or for what to eat over a number of days. Builds a plan of 1 to 7 days from Foodbe's recipes, within an optional dollar budget for the whole plan, filtered by the diet and allergies you send. Returns outcome "served" with the plan and its insight: the taste the plan is missing, the food group it is short on, the health roles it covers, and its cheapest, priciest and quickest meal. Every line comes from Foodbe's stored data, never from a model. If no plan can be built, it returns outcome "not_found" and costs nothing. A limited number of calls work without a key. After that, a key is needed in the x-foodbe-key header.

Parametersdaysdietbudgetallergies

foodbe_grocery_list

Build a grocery list

Call this when a user asks for a grocery or shopping list. Send a dish for the list of one recipe, or days and a budget for the list of a meal plan. Do not send both. Returns outcome "served" with the list items, the cost of each and the total. Every line comes from Foodbe's stored data, never from a model. If no list can be built, it returns outcome "not_found" and costs nothing. A limited number of calls work without a key. After that, a key is needed in the x-foodbe-key header.

Parametersdaysdietdishbudgetallergies

foodbe_feedback

Send feedback to Foodbe

Call when a Foodbe tool is missing, an answer was wrong or too thin, or a tool you need does not exist. Tell us what would help you. Free: no tokens are charged. Returns outcome "received". The number of messages per day is limited.

Parameterskindtoolmessagerequired

Version history

3
  1. v3.1.0LatestNov 5, 2026
  2. v3.0.0Nov 3, 2026
  3. v1.0.0Oct 26, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.