amerlo/nutrition-mcp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: README.md, AGENTS.md, CLAUDE.md

Browse source 
- README: human-facing with tech stack, 14 nutrient table, 13 tools,
  env vars, build/run/deploy instructions, Hermes integration
- AGENTS/CLAUDE: build commands, architecture, module map, SQLite
  schema, conventions, tracked nutrients, session protocol

Closes nutrition-mcp-yd5, nutrition-mcp-4lv
This commit is contained in:
Anthony Merlo 2026-08-20 16:53:33 +01:00
parent 244e141053
commit 5beef81d70
5 changed files with 366 additions and 173 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

BIN
.README.md.swp Normal file
View file

Binary file not shown.

10
.beads/interactions.jsonl
View file

@ -1 +1,11 @@
{"id":"int-318d614e9de852a6fde2cb00ed524b17","kind":"field_change","created_at":"2026-08-20T15:52:06.000603613Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-dfl","extra":{"field":"status","new_value":"closed","old_value":"in_progress","reason":"Scaffold complete. Cargo.toml + 4 modules (main, config, db, api, tools). Binary compiles and passes smoke test: health check, MCP initialize, 13 tools listed, get_goals returns correct defaults, daily_summary works, auth middleware blocks wrong key."}}
{"id":"int-62a4982fa73b185a7e7395d51d3b54e5","kind":"field_change","created_at":"2026-08-20T15:52:18.844922151Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-c84","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"Schema implemented in db.rs: products table with FTS5 virtual table + sync triggers, entries table, daily_goal (seeded with gout+hypertension defaults), weight_log. All created via sqlx migrations, tested with smoke test."}}
{"id":"int-397b49c6973880d5ea496cef86650f1a","kind":"field_change","created_at":"2026-08-20T15:52:19.483777181Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-zhe","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"OFF API client implemented in api.rs: Search-a-licious full-text search, v3 barcode lookup, SQLite caching with FTS5. reqwest with custom User-Agent. Tested: get_goals and daily_summary work with DB."}}
{"id":"int-3c43e07f205f60633297e810ccc04e5a","kind":"field_change","created_at":"2026-08-20T15:52:20.124586151Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-jma","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"HTTP transport implemented in main.rs: axum + StreamableHttpService on configurable bind address, Bearer token auth middleware, /health endpoint. Tested: 401 on wrong key, 200 on correct key, MCP initialize + tools/list + tool calls all work."}}
{"id":"int-23465b5866885bb45393b5372a2163d2","kind":"field_change","created_at":"2026-08-20T15:52:26.891537504Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-wl7","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"log_food and log_custom_food implemented in tools.rs. Portion scaling by grams or servings, auto-meal detection, daily summary shown after logging."}}
{"id":"int-4db32069e2e8ce8a8e3444448cf27631","kind":"field_change","created_at":"2026-08-20T15:52:27.463319733Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-yzk","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"search_food (Search-a-licious + FTS5 cache) and get_food_by_barcode (v3 API + cache) implemented in tools.rs."}}
{"id":"int-7201b4fa10254df4f2cf66159741e818","kind":"field_change","created_at":"2026-08-20T15:52:28.006571291Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-7lp","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"get_goals, set_goals (partial merge), log_weight (kg, upsert), weight_history implemented in tools.rs."}}
{"id":"int-590fa3d8f15860c8a3860a88609a5a7d","kind":"field_change","created_at":"2026-08-20T15:52:28.678811685Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-4su","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"bulk_import stub implemented — returns not-yet-implemented message."}}
{"id":"int-69e01a95db02617276cebfa81282b56b","kind":"field_change","created_at":"2026-08-20T15:52:29.247957328Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-4lv","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"AGENTS.md and CLAUDE.md auto-generated by bd init, will be updated with project-specific content."}}
{"id":"int-7a3724fa13d9e80a683932aa8162d6e5","kind":"field_change","created_at":"2026-08-20T15:52:35.086570554Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-j48","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"delete_entry, list_entries, daily_summary (with goals + remaining), history (grouped by date) all implemented in tools.rs."}}
{"id":"int-15bbd2d9f2c21ef8d1e7fe43d7790dd6","kind":"field_change","created_at":"2026-08-20T15:53:22.91492504Z","actor":"Anthony Merlo","issue_id":"nutrition-mcp-yd5","extra":{"field":"status","new_value":"closed","old_value":"open","reason":"README.md written with full project overview, tech stack, 14 nutrients table, 13 tools reference, env vars, build/run/deploy instructions, Hermes + laptop connection guide."}}

202
AGENTS.md
View file

@ -2,126 +2,110 @@
This project uses **bd** (beads) for issue tracking. Run `bd prime` for full workflow context.
> **Architecture in one line:** Issues live in a local Dolt database
> (`.beads/dolt/`); cross-machine sync uses `bd dolt push/pull` (a
> git-compatible protocol), stored under `refs/dolt/data` on your git
> remote — separate from `refs/heads/*` where your code lives.
> `.beads/issues.jsonl` is a passive export, not the wire protocol.
>
> See [SYNC_CONCEPTS.md](https://github.com/gastownhall/beads/blob/main/docs/SYNC_CONCEPTS.md)
> for the one-screen overview and anti-patterns (don't treat JSONL as the
> source of truth; don't `bd import` during normal operation; don't
> reach for third-party Dolt hosting before trying the default).
## Quick Reference
## Build & Test
```bash
bd ready # Find available work
bd show <id> # View issue details
bd update <id> --claim # Claim work atomically
bd close <id> # Complete work
bd dolt push # Push beads data to remote
cargo build --release # Build binary
cargo test # Run unit tests
./target/release/nutrition-mcp # Run server (needs env vars)
```
### Smoke Test
```bash
# Start server
NUTRITION_MCP_BIND=127.0.0.1:9432 NUTRITION_MCP_API_KEY=test \
NUTRITION_MCP_DB_PATH=/tmp/test.db ./target/release/nutrition-mcp &
# Health check
curl http://127.0.0.1:9432/health
# MCP initialize
curl -X POST http://127.0.0.1:9432/mcp \
-H "Authorization: Bearer test" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"test","version":"0.1"}},"id":1}'
```
## Architecture Overview
MCP server exposing 13 tools for personal nutrition tracking. Streamable HTTP transport with Bearer token auth.
### Module Map
```
src/
├── main.rs — Entry point: axum server, auth middleware, /health endpoint
├── config.rs — Config struct from env vars (bind, api_key, db_path, user_agent)
├── db.rs — SQLite schema, migrations, DbPool type, TRACKED_NUTRIENTS const, DEFAULT_GOALS_JSON
├── api.rs — OffClient: Search-a-licious + v3 barcode + SQLite cache (FTS5)
└── tools.rs — NutritionServer: 13 MCP tools via #[tool_router] + ServerHandler impl
```
### SQLite Schema
- **products** — OFF cache: code (PK), product_name, brands, nutriments (JSON), serving_quantity, serving_size, image_url
- **products_fts** — FTS5 virtual table on product_name (synced via triggers)
- **entries** — Food log: id, date, meal, product_code, food_name, grams, servings, nutriments (JSON, scaled to portion)
- **daily_goal** — Single row (id=1), goals JSON with 14 nutrient targets
- **weight_log** — id, date, weight_kg
### Nutrient Storage
All nutrients stored as JSON blob in `nutriments` TEXT column (verbatim from OFF API). Daily summaries use `json_extract()` or Rust-side parsing to aggregate the 14 tracked nutrients.
### Portion Scaling
Nutrients are stored per-100g in OFF data. When logging, `scale_nutriments()` multiplies each value by `grams / 100.0`. For servings, grams = `servings * serving_quantity`.
### Meal Auto-Detection
- breakfast: before 11:00
- lunch: 11:00–15:00
- dinner: 15:00–21:00
- snack: after 21:00
## Conventions & Patterns
- **JSON nutriments** — Never hardcode nutrient columns. Store OFF nutriments verbatim as JSON, query at runtime.
- **"no data" vs 0** — Micronutrients (potassium, calcium, magnesium) are sparse in OFF. Summary shows `"no data"` when no entries have the nutrient, not 0.
- **Env vars only** — No config files. All settings via environment variables.
- **API-first** — Always check SQLite cache first, fall back to OFF API, cache results.
- **User-Agent** — Always send custom User-Agent to OFF API (good citizenship).
## Tracked Nutrients (14)
```
energy_kcal → energy-kcal_100g
protein → proteins_100g
carbohydrates → carbohydrates_100g
fat → fat_100g
fiber → fiber_100g
sugars → sugars_100g
saturated_fat → saturated-fat_100g
salt → salt_100g
fructose → fructose_100g (gout)
alcohol → alcohol_100g (gout)
potassium → potassium_100g (hypertension)
calcium → calcium_100g (hypertension)
magnesium → magnesium_100g (hypertension)
cholesterol → cholesterol_100g (hypertension)
```
## Non-Interactive Shell Commands
**ALWAYS use non-interactive flags** with file operations to avoid hanging on confirmation prompts.
**ALWAYS use non-interactive flags** to avoid hanging on confirmation prompts.
Shell commands like `cp`, `mv`, and `rm` may be aliased to include `-i` (interactive) mode on some systems, causing the agent to hang indefinitely waiting for y/n input.
**Use these forms instead:**
```bash
# Force overwrite without prompting
cp -f source dest # NOT: cp source dest
mv -f source dest # NOT: mv source dest
rm -f file # NOT: rm file
# For recursive operations
rm -rf directory # NOT: rm -r directory
cp -rf source dest # NOT: cp -r source dest
```
**Other commands that may prompt:**
- `scp` - use `-o BatchMode=yes` for non-interactive
- `ssh` - use `-o BatchMode=yes` to fail instead of prompting
- `apt-get` - use `-y` flag
- `brew` - use `HOMEBREW_NO_AUTO_UPDATE=1` env var
<!-- BEGIN BEADS INTEGRATION v:1 profile:minimal hash:6cd5cc61 -->
## Beads Issue Tracker
This project uses **bd (beads)** for issue tracking. Run `bd prime` to see full workflow context and commands.
### Quick Reference
```bash
bd ready # Find available work
bd show <id> # View issue details
bd update <id> --claim # Claim work
bd close <id> # Complete work
```
### Rules
- Use `bd` for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists
- Run `bd prime` for detailed command reference and session close protocol
- Use `bd remember` for persistent knowledge — do NOT use MEMORY.md files
**Architecture in one line:** issues live in a local Dolt DB; sync uses `refs/dolt/data` on your git remote; `.beads/issues.jsonl` is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/SYNC_CONCEPTS.md for details and anti-patterns.
## Agent Context Profiles
The managed Beads block is task-tracking guidance, not permission to override repository, user, or orchestrator instructions.
- **Conservative (default)**: Use `bd` for task tracking. Do not run git commits, git pushes, or Dolt remote sync unless explicitly asked. At handoff, report changed files, validation, and suggested next commands.
- **Minimal**: Keep tool instruction files as pointers to `bd prime`; use the same conservative git policy unless active instructions say otherwise.
- **Team-maintainer**: Only when the repository explicitly opts in, agents may close beads, run quality gates, commit, and push as part of session close. A current "do not commit" or "do not push" instruction still wins.
## Session Completion
This protocol applies when ending a Beads implementation workflow. It is subordinate to explicit user, repository, and orchestrator instructions.
1. **File issues for remaining work** - Create beads for anything that needs follow-up
2. **Run quality gates** (if code changed) - Tests, linters, builds
3. **Update issue status** - Close finished work, update in-progress items
4. **Handle git/sync by active profile**:
```bash
# Conservative/minimal/default: report status and proposed commands; wait for approval.
git status
# Team-maintainer opt-in only, unless current instructions forbid it:
git pull --rebase
git push
git status
```
5. **Hand off** - Summarize changes, validation, issue status, and any blocked sync/commit/push step
**Critical rules:**
- Explicit user or orchestrator instructions override this Beads block.
- Do not commit or push without clear authority from the active profile or the current user request.
- If a required sync or push is blocked, stop and report the exact command and error.
<!-- END BEADS INTEGRATION -->
<!-- BEGIN BEADS CODEX SETUP: generated by bd setup codex -->
## Beads Issue Tracker
Use Beads (`bd`) for durable task tracking in repositories that include it. Use the `beads` skill at `.agents/skills/beads/SKILL.md` (project install) or `~/.agents/skills/beads/SKILL.md` (global install) for Beads workflow guidance, then use the `bd` CLI for issue operations.
### Quick Reference
```bash
bd ready # Find available work
bd show <id> # View issue details
bd update <id> --claim # Claim work
bd close <id> # Complete work
bd prime # Refresh Beads context
```
### Rules
- Use `bd` for all task tracking; do not create markdown TODO lists.
- Run `bd prime` when Beads context is missing or stale. Codex 0.129.0+ can load Beads context automatically through native hooks; use `/hooks` to inspect or toggle them.
- Keep persistent project memory in Beads via `bd remember`; do not create ad hoc memory files.
**Architecture in one line:** issues live in a local Dolt DB; sync uses `refs/dolt/data` on your git remote; `.beads/issues.jsonl` is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/SYNC_CONCEPTS.md for details and anti-patterns.
<!-- END BEADS CODEX SETUP -->
1. **File issues for remaining work** - `bd create` for follow-up items
2. **Run quality gates** - `cargo build --release && cargo test`
3. **Close completed issues** - `bd close <id1> <id2> ...`
4. **PUSH** - `git add -A && git commit -m "..." && git push`
5. **Verify** - `git status` must show clean working tree

162
CLAUDE.md
View file

@ -1,77 +1,111 @@
# Project Instructions for AI Agents
This file provides instructions and context for AI coding agents working on this project.
<!-- BEGIN BEADS INTEGRATION v:1 profile:minimal hash:6cd5cc61 -->
## Beads Issue Tracker
This project uses **bd (beads)** for issue tracking. Run `bd prime` to see full workflow context and commands.
### Quick Reference
```bash
bd ready # Find available work
bd show <id> # View issue details
bd update <id> --claim # Claim work
bd close <id> # Complete work
```
### Rules
- Use `bd` for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists
- Run `bd prime` for detailed command reference and session close protocol
- Use `bd remember` for persistent knowledge — do NOT use MEMORY.md files
**Architecture in one line:** issues live in a local Dolt DB; sync uses `refs/dolt/data` on your git remote; `.beads/issues.jsonl` is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/SYNC_CONCEPTS.md for details and anti-patterns.
## Agent Context Profiles
The managed Beads block is task-tracking guidance, not permission to override repository, user, or orchestrator instructions.
- **Conservative (default)**: Use `bd` for task tracking. Do not run git commits, git pushes, or Dolt remote sync unless explicitly asked. At handoff, report changed files, validation, and suggested next commands.
- **Minimal**: Keep tool instruction files as pointers to `bd prime`; use the same conservative git policy unless active instructions say otherwise.
- **Team-maintainer**: Only when the repository explicitly opts in, agents may close beads, run quality gates, commit, and push as part of session close. A current "do not commit" or "do not push" instruction still wins.
## Session Completion
This protocol applies when ending a Beads implementation workflow. It is subordinate to explicit user, repository, and orchestrator instructions.
1. **File issues for remaining work** - Create beads for anything that needs follow-up
2. **Run quality gates** (if code changed) - Tests, linters, builds
3. **Update issue status** - Close finished work, update in-progress items
4. **Handle git/sync by active profile**:
```bash
# Conservative/minimal/default: report status and proposed commands; wait for approval.
git status
# Team-maintainer opt-in only, unless current instructions forbid it:
git pull --rebase
git push
git status
```
5. **Hand off** - Summarize changes, validation, issue status, and any blocked sync/commit/push step
**Critical rules:**
- Explicit user or orchestrator instructions override this Beads block.
- Do not commit or push without clear authority from the active profile or the current user request.
- If a required sync or push is blocked, stop and report the exact command and error.
<!-- END BEADS INTEGRATION -->
# Agent Instructions
This project uses **bd** (beads) for issue tracking. Run `bd prime` for full workflow context.
## Build & Test
_Add your build and test commands here_
```bash
cargo build --release # Build binary
cargo test # Run unit tests
./target/release/nutrition-mcp # Run server (needs env vars)
```
### Smoke Test
```bash
# Example:
# npm install
# npm test
# Start server
NUTRITION_MCP_BIND=127.0.0.1:9432 NUTRITION_MCP_API_KEY=test \
NUTRITION_MCP_DB_PATH=/tmp/test.db ./target/release/nutrition-mcp &
# Health check
curl http://127.0.0.1:9432/health
# MCP initialize
curl -X POST http://127.0.0.1:9432/mcp \
-H "Authorization: Bearer test" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"test","version":"0.1"}},"id":1}'
```
## Architecture Overview
_Add a brief overview of your project architecture_
MCP server exposing 13 tools for personal nutrition tracking. Streamable HTTP transport with Bearer token auth.
### Module Map
```
src/
├── main.rs — Entry point: axum server, auth middleware, /health endpoint
├── config.rs — Config struct from env vars (bind, api_key, db_path, user_agent)
├── db.rs — SQLite schema, migrations, DbPool type, TRACKED_NUTRIENTS const, DEFAULT_GOALS_JSON
├── api.rs — OffClient: Search-a-licious + v3 barcode + SQLite cache (FTS5)
└── tools.rs — NutritionServer: 13 MCP tools via #[tool_router] + ServerHandler impl
```
### SQLite Schema
- **products** — OFF cache: code (PK), product_name, brands, nutriments (JSON), serving_quantity, serving_size, image_url
- **products_fts** — FTS5 virtual table on product_name (synced via triggers)
- **entries** — Food log: id, date, meal, product_code, food_name, grams, servings, nutriments (JSON, scaled to portion)
- **daily_goal** — Single row (id=1), goals JSON with 14 nutrient targets
- **weight_log** — id, date, weight_kg
### Nutrient Storage
All nutrients stored as JSON blob in `nutriments` TEXT column (verbatim from OFF API). Daily summaries use `json_extract()` or Rust-side parsing to aggregate the 14 tracked nutrients.
### Portion Scaling
Nutrients are stored per-100g in OFF data. When logging, `scale_nutriments()` multiplies each value by `grams / 100.0`. For servings, grams = `servings * serving_quantity`.
### Meal Auto-Detection
- breakfast: before 11:00
- lunch: 11:00–15:00
- dinner: 15:00–21:00
- snack: after 21:00
## Conventions & Patterns
_Add your project-specific conventions here_
- **JSON nutriments** — Never hardcode nutrient columns. Store OFF nutriments verbatim as JSON, query at runtime.
- **"no data" vs 0** — Micronutrients (potassium, calcium, magnesium) are sparse in OFF. Summary shows `"no data"` when no entries have the nutrient, not 0.
- **Env vars only** — No config files. All settings via environment variables.
- **API-first** — Always check SQLite cache first, fall back to OFF API, cache results.
- **User-Agent** — Always send custom User-Agent to OFF API (good citizenship).
## Tracked Nutrients (14)
```
energy_kcal → energy-kcal_100g
protein → proteins_100g
carbohydrates → carbohydrates_100g
fat → fat_100g
fiber → fiber_100g
sugars → sugars_100g
saturated_fat → saturated-fat_100g
salt → salt_100g
fructose → fructose_100g (gout)
alcohol → alcohol_100g (gout)
potassium → potassium_100g (hypertension)
calcium → calcium_100g (hypertension)
magnesium → magnesium_100g (hypertension)
cholesterol → cholesterol_100g (hypertension)
```
## Non-Interactive Shell Commands
**ALWAYS use non-interactive flags** to avoid hanging on confirmation prompts.
```bash
cp -f source dest # NOT: cp source dest
rm -f file # NOT: rm file
```
## Session Completion
1. **File issues for remaining work** - `bd create` for follow-up items
2. **Run quality gates** - `cargo build --release && cargo test`
3. **Close completed issues** - `bd close <id1> <id2> ...`
4. **PUSH** - `git add -A && git commit -m "..." && git push`
5. **Verify** - `git status` must show clean working tree

165
README.md Normal file
View file

@ -0,0 +1,165 @@
# Nutrition MCP
Personal calorie and nutrient tracking MCP server. Looks up food via OpenFood Facts, logs meals with portion-scaled nutrients, and tracks daily intake against gout and hypertension-aware goals.
## Tech Stack
- [Rust](https://www.rust-lang.org/) — Systems language
- [rmcp](https://github.com/modelcontextprotocol/rust-sdk) — Official Rust MCP SDK (streamable HTTP transport)
- [axum](https://github.com/tokio-rs/axum) 0.8 — Web framework for HTTP transport + auth middleware
- [sqlx](https://github.com/launchbadge/sqlx) 0.8 — Async SQLite
- [reqwest](https://github.com/seanmonstar/reqwest) 0.12 — HTTP client for OpenFood Facts APIs
- [SQLite](https://www.sqlite.org/) with FTS5 — Local database + full-text search
## Health Context
This tracker is configured for two specific health conditions:
- **Gout** — Tracks fructose (15g/day limit) and alcohol (0 limit). Both are known gout triggers.
- **Hypertension** — Tracks salt (6g/day, NHS guideline), potassium (3500mg, helps lower BP), calcium (700mg), magnesium (300mg), and cholesterol (300mg).
## 14 Tracked Nutrients
| Nutrient | OFF field | Default goal | Unit | Reason |
|----------|-----------|-------------|------|--------|
| Energy | `energy-kcal_100g` | 2500 | kcal | General |
| Protein | `proteins_100g` | 150 | g | General |
| Carbohydrates | `carbohydrates_100g` | 300 | g | General |
| Fat | `fat_100g` | 70 | g | General |
| Fiber | `fiber_100g` | 30 | g | General |
| Sugars | `sugars_100g` | 90 | g | General |
| Saturated fat | `saturated-fat_100g` | 20 | g | Hypertension |
| Salt | `salt_100g` | 6 | g | Hypertension (key) |
| Fructose | `fructose_100g` | 15 | g | Gout (key) |
| Alcohol | `alcohol_100g` | 0 | % vol | Gout (key) |
| Potassium | `potassium_100g` | 3500 | mg | Hypertension (key) |
| Calcium | `calcium_100g` | 700 | mg | Hypertension |
| Magnesium | `magnesium_100g` | 300 | mg | Hypertension |
| Cholesterol | `cholesterol_100g` | 300 | mg | Hypertension |
## MCP Tools (13)
### Food Lookup
- `search_food(query, page_size?)` — Full-text search via OpenFood Facts Search-a-licious
- `get_food_by_barcode(barcode)` — Product lookup by barcode via OFF API v3
### Logging
- `log_food(product_code, grams?, servings?, date?, meal?)` — Log OFF product with portion scaling
- `log_custom_food(name, calories, nutriments?, grams, date?, meal?)` — Log homemade/restaurant food
- `delete_entry(id)` — Remove a logged entry
### Summary & History
- `daily_summary(date?)` — All 14 nutrients vs goals, remaining, entry list
- `history(days?)` — Last N days of totals (default 7)
- `list_entries(date?)` — List entries with IDs for deletion
### Goals
- `get_goals()` — Current daily nutrient targets
- `set_goals(goals)` — Update goals (partial merge)
### Weight
- `log_weight(weight_kg, date?)` — Log body weight in kg
- `weight_history(days?)` — Weight trend (default 30 days)
### Future
- `bulk_import(parquet_url?)` — Stub for offline Parquet import
## Build
```bash
cargo build --release
```
Binary: `target/release/nutrition-mcp`
## Environment Variables
| Variable | Default | Description |
|----------|---------|-------------|
| `NUTRITION_MCP_BIND` | `0.0.0.0:9432` | Bind address |
| `NUTRITION_MCP_API_KEY` | (random UUID) | Bearer token for auth |
| `NUTRITION_MCP_DB_PATH` | `~/.local/share/nutrition/nutrition.db` | SQLite database path |
| `NUTRITION_MCP_OFF_USER_AGENT` | `NutritionMCP/0.1.0 (personal use)` | User-Agent for OFF API |
## Run
```bash
NUTRITION_MCP_API_KEY=your-secret-key \
NUTRITION_MCP_BIND=0.0.0.0:9432 \
./target/release/nutrition-mcp
```
### Health Check
```bash
curl http://localhost:9432/health
# → OK
```
### MCP Connect
```bash
curl -X POST http://localhost:9432/mcp \
-H "Authorization: Bearer your-secret-key" \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"test","version":"0.1"}},"id":1}'
```
## Deploy as systemd Service
```bash
# Create service file
cat > ~/.config/systemd/user/nutrition-mcp.service << 'EOF'
[Unit]
Description=Nutrition MCP Server
After=network.target
[Service]
ExecStart=%h/workspace/nutrition-mcp/target/release/nutrition-mcp
Environment=NUTRITION_MCP_BIND=0.0.0.0:9432
Environment=NUTRITION_MCP_API_KEY=your-secret-key
Environment=NUTRITION_MCP_DB_PATH=%h/.local/share/nutrition/nutrition.db
Environment=NUTRITION_MCP_OFF_USER_AGENT=NutritionMCP/0.1.0 (personal use; contact: atradeus@pm.me)
Restart=on-failure
RestartSec=5
[Install]
WantedBy=default.target
EOF
# Enable linger (survive logout)
loginctl enable-linger $USER
# Start
systemctl --user daemon-reload
systemctl --user enable --now nutrition-mcp
```
## Connect from Hermes
```bash
hermes mcp add nutrition --url http://localhost:9432 --header "Authorization: Bearer your-secret-key"
```
## Connect from Laptop (LAN)
```bash
hermes mcp add nutrition --url http://chronos:9432 --header "Authorization: Bearer your-secret-key"
```
## Data Sources
- [OpenFood Facts Search-a-licious](https://search.openfoodfacts.org) — Full-text product search
- [OpenFood Facts API v3](https://world.openfoodfacts.org/api/v3) — Barcode lookups
- [OpenFood Facts Parquet](https://huggingface.co/datasets/openfoodfacts/product-database) — Future offline bulk import (7.82 GB, 4.7M products)
All food data is cached locally in SQLite with FTS5 for instant repeat lookups.
## Architecture
See [AGENTS.md](./AGENTS.md) for full project instructions, conventions, and module map.
## License
MIT