FoodGuard

Verified food-safety screening for AI agents.

FoodGuard is an open-source MCP server and Claude Agent Skill that gives AI agents deterministic, source-grounded tools for food allergens, Indian packaged-food labels, official regulations, recalls, and preliminary process hazards.

It is infrastructure for trustworthy agents—not an "AI food-safety expert" prompt.

Why it exists

Small food businesses and consumers increasingly ask AI systems consequential questions. Model memory alone is a poor source for rules that change, differ by jurisdiction, and can affect health. FoodGuard makes those systems show their work:

User → Claude / MCP host → FoodGuard rule engine → official evidence → grounded answer

Every finding carries an outcome, confidence, matched input, source IDs, official URLs, retrieval dates, limitations, and a clear screening boundary.

Related MCP server: food-safety-mcp

What v0.1 can do

Quick start

Requirements: Python 3.11+ and uv.

git clone https://github.com/TechTharun/foodguard.git
cd foodguard
uv sync --extra dev
uv run foodguard-mcp

The server uses stdio by default. The repository includes .mcp.json, so project-aware Claude Code sessions can discover it after dependencies are installed.

To inspect the server interactively:

uv run mcp dev src/foodguard/server.py

Example

Ask Claude:

Use FoodGuard to identify allergens in wheat flour, sodium caseinate, soy lecithin, peanut, and natural flavour.

FoodGuard returns structured findings resembling:

{
  "outcome": "REVIEW_REQUIRED",
  "findings": [
    {"code": "ALLERGEN_CEREALS_GLUTEN", "outcome": "DETECTED"},
    {"code": "ALLERGEN_MILK", "outcome": "DETECTED"},
    {"code": "ALLERGEN_SOYBEAN", "outcome": "DETECTED"},
    {"code": "ALLERGEN_GROUNDNUT", "outcome": "DETECTED"},
    {"code": "ALLERGEN_AMBIGUOUS_INGREDIENT", "outcome": "REVIEW_REQUIRED"}
  ],
  "disclaimer": "Screening result only..."
}

Claude can explain the result, but the evidence and abstention behavior come from FoodGuard.

Claude Agent Skill

The bundled skill is at .claude/skills/food-safety/SKILL.md. It teaches Claude when to call each tool, how to preserve uncertainty, and when to escalate to official or professional review. It includes short reference files for evidence policy and multi-tool workflows.

FoodGuard-Eval

The starter benchmark contains 30 transparent cases covering direct allergens, derivatives, multiple allergens, negatives, and correct abstention.

uv run foodguard-eval
uv run pytest
uv run ruff check .

CI runs linting, unit tests, an in-memory MCP client test, and the benchmark on Python 3.11 and 3.12. Benchmark scores in this repository are computed—never hand-written.

Design principles

• Evidence before eloquence: official sources and limitations travel with claims.

• Abstention is a feature: missing or ambiguous data produces review, not confident prose.

• Deterministic core: the MCP server wraps ordinary testable Python functions.

• Jurisdiction first: India rules are explicit rather than silently generalized worldwide.

• No hidden live claims: v0.1 tells you when a live source must be checked.

• Agent-agnostic: Claude is the first-class experience, but any MCP-compatible host can use the server.

Read the architecture, evidence contract, and safety model.

Roadmap

• verified FSSAI amendment monitoring and source diffs;

• reliable live recall ingestion with provenance;

• label-image OCR with bounding-box evidence;

• supplier-specification and compound-ingredient workflows;

• larger expert-reviewed public evals;

• additional jurisdictions behind separate rule packs.

Contributing

Food-safety professionals, developers, researchers, translators, and accessibility reviewers are welcome. Start with CONTRIBUTING.md. Please report security problems privately as described in SECURITY.md.

License

Apache-2.0. See LICENSE.