io.github.cphoskinsPublished by GitHub account cphoskinsv2.4.2Updated Nov 3, 2026
MCP server for Cronometer — food logs, macros, fasting, biometrics, and recurring foods
Connects an assistant to a Cronometer Gold account to read food logs, macros, micronutrients, fasting and biometrics, and to edit diary entries and targets.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
An MCP (Model Context Protocol) server that provides access to your Cronometer nutrition data. Pull detailed food logs, daily macro/micro summaries, manage diary entries, fasting, biometrics, and recurring foods — all from Claude, Cursor, or any MCP-compatible client.
Requires a Cronometer Gold account (or any paid tier that supports web login).
Or install from source:
Or add them to a .env file in your project root (if your MCP client supports it).
.mcp.json)claude_desktop_config.json)If you installed from source with pip install -e ., you can also use the full Python path:
Set CRONOMETER_READ_ONLY=1 (also accepts true or yes) in the server's env to expose only the
read tools. The 13 tools that change your Cronometer account are not registered at all, so the
client never sees them: adding or removing food entries, macro targets, schedules and templates,
fasts, biometrics, copy day, mark day complete, and repeat items. sync_cronometer stays available;
it only writes files on your machine.
This limits what the server offers, not what your credentials can do. Cronometer has no read-only
login, so the password in env still has full access to the account.
By default the server talks to its client over stdio. To run it on another machine or in a
container, set CRONOMETER_TRANSPORT=streamable-http and it serves the MCP endpoint at
http://<host>:<port>/mcp instead.
In Docker, against the published package, reachable as your-server on your network:
CRONOMETER_ALLOWED_HOSTS matters: the MCP SDK checks Host and Origin headers on its own only
when bound to loopback. On any other bind it accepts every Host, which lets a web page you happen
to open on the same network reach the server through DNS rebinding. With the allowlist set,
requests whose Host or Origin is not on it get 421 or 403. Without it the server logs a
warning at startup and runs anyway.
Then point the client at the URL. Claude Code (.mcp.json):
The endpoint has no authentication. Anyone who can reach the port can read and change the
Cronometer account whose credentials the server holds. Keep it bound to 127.0.0.1, or put it on
a network only you can reach (a VPN or Tailscale keeps strangers out; it does not stop the DNS
rebinding case above, so set the allowlist as well) or behind a reverse proxy that authenticates.
Adding CRONOMETER_READ_ONLY=1 narrows what a remote client can do, with the same caveat as above:
the credentials themselves keep full access.
All date parameters use YYYY-MM-DD format. Most tools default to today or the last 7 days when dates are omitted.
Key parameter patterns:
diary_group — a diary group name (case-insensitive) or a 0-based index.
Cronometer Gold gives every account 8 diary group slots and lets you rename and
enable them freely, so the names are account-specific and are not always
Breakfast/Lunch/Dinner/Snacks. Call list_diary_groups to see yours. On an
untouched account the four standard meals are indices 1–4 (index 0 is a
slot that ships disabled). Unknown names, disabled groups, and out-of-range
indices are rejected rather than silently defaulting — Cronometer itself
accepts a bad index without complaint and the entry becomes unreachable.days_of_week — "all", "weekdays", "weekends", or comma-separated day numbers (0=Sun through 6=Sat)measure_id — pass 0 to use the universal gram-based measure (works for all food sources)target_date — pass "all" on get_macro_targets to get the full weekly scheduleThe sync_cronometer tool saves files to ~/.local/share/cronometer-mcp/ by default. Override with the CRONOMETER_DATA_DIR environment variable:
Output files:
exports/servings_{start}_{end}.jsonexports/daily_summary_{start}_{end}.jsonexports/servings_latest.jsonexports/daily_summary_latest.jsonfood-log.mdCronometer does not have a public API for individual users. This server uses the same GWT-RPC (Google Web Toolkit Remote Procedure Call) protocol that the Cronometer web app uses internally:
authenticate to get a user IDgenerateAuthorizationToken for short-lived export tokensSession cookies are persisted to ~/.local/share/cronometer-mcp/.session_cookies so that subsequent invocations reuse the session without re-authenticating (Cronometer has aggressive login rate limiting).
The GWT protocol uses a permutation hash and header value that are baked into each Cronometer web deploy. These values are hardcoded in the client and may break when Cronometer pushes a new build.
Current values (as of February 2026):
7B121DC5483BF272B1BC1916DA9FA9632D6A926E3729946302DC68073CB0D550If authentication starts failing with GWT errors, these values likely need updating. You can find the current values by:
cronometer.com/cronometer/appx-gwt-permutation header and the payload structureYou can override them via the CronometerClient constructor:
You can also use the client directly in Python:
MIT
Source: README.md at commit 3157ff9
Get detailed food log with individual food entries and full nutrition. Returns every food entry with macros and micronutrients. Great for analyzing what was eaten and spotting nutrient gaps. Args: start_date: Start date as YYYY-MM-DD (defaults to today). end_date: End date as YYYY-MM-DD (defaults to today).
end_datestart_dateGet daily nutrition summary with macro totals per day. Returns calorie, protein, carb, fat, and fiber totals for each day. Use this for quick daily overviews and trend analysis. Args: start_date: Start date as YYYY-MM-DD (defaults to 7 days ago). end_date: End date as YYYY-MM-DD (defaults to today).
end_datestart_dateGet detailed micronutrient breakdown for meal planning. Shows vitamins, minerals, and other micronutrients per day with period averages. Use this to identify nutrient gaps and plan meals. Args: start_date: Start date as YYYY-MM-DD (defaults to 7 days ago). end_date: End date as YYYY-MM-DD (defaults to today).
end_datestart_dateExport raw CSV data from Cronometer for any data type. Useful when you need the full unprocessed export. Args: export_type: One of 'servings', 'daily_summary', 'exercises', 'biometrics', 'notes'. start_date: Start date as YYYY-MM-DD (defaults to today). end_date: End date as YYYY-MM-DD (defaults to today).
end_datestart_dateexport_typerequiredList this account's diary groups, with the values add_food_entry accepts. Diary group names are user-configured in Cronometer, so they are NOT always Breakfast/Lunch/Dinner/Snacks. Call this before assuming a name exists — an account may rename any slot or enable extra ones. Returns each group's wire_index (the 0-based value add_food_entry takes), its name, and whether it is enabled. Only enabled groups can be written to.
Takes no parameters.
Search Cronometer's food database by name. Returns matching foods with their IDs and source information needed to add a serving (food_id, food_source_id, measure_id). Args: query: Food name or keyword to search for (e.g. "eggs", "chicken breast").
queryrequiredGet detailed food information including available serving measures. Use this after search_foods to get the measure_id needed for add_food_entry. Returns all available serving sizes with their numeric IDs and gram weights. Args: food_source_id: Food source ID from search_foods results.
food_source_idrequiredAdd a food entry to the Cronometer diary. Use search_foods to find food_id and food_source_id, then get_food_details for measure_id and weight_grams. For CRDB/custom foods, you can omit measure_id (defaults to a universal NCCDB measure that works for all food sources). When measure_id is omitted, quantity is set to weight_grams. Args: food_id: Numeric food ID from search_foods results. food_source_id: Food source ID from search_foods results. weight_grams: Weight of the serving in grams. date: Date to log the entry as YYYY-MM-DD (e.g. "2026-03-04"). measure_id: Measure/unit ID. Pass 0 (default) to use the universal measure that works for all food sources. quantity: Number of servings. Defaults to weight_grams when measure_id is 0 (universal gram-based measure). diary_group: Diary group name (case-insensitive) or 0-based index. Names are user-configured and are not always Breakfast/Lunch/Dinner/Snacks — call list_diary_groups to see this account's groups. Defaults to a time-of-day choice among enabled groups if omitted.
daterequiredfood_idrequiredquantitymeasure_iddiary_groupweight_gramsrequiredfood_source_idrequiredRemove a food entry from the Cronometer diary. Args: serving_id: The serving ID returned by add_food_entry (e.g. "D80lp$").
serving_idrequiredGet current daily macro targets from Cronometer. Returns the effective macro targets (protein, fat, carbs, calories) and the template name for a specific date or all days of the week. A macro with no target set in Cronometer is null. Args: target_date: Date as YYYY-MM-DD to get targets for (defaults to today). Pass "all" to get the full weekly schedule.
target_dateUpdate daily macro targets in Cronometer. Reads current targets first, then updates only the provided values. Omitted values remain unchanged. Args: protein_grams: Protein target in grams. fat_grams: Fat target in grams. carbs_grams: Net carbs target in grams. calories: Calorie target in kcal. target_date: Date as YYYY-MM-DD (defaults to today). template_name: Template name (defaults to "Custom Targets").
caloriesfat_gramscarbs_gramstarget_dateprotein_gramstemplate_nameSet the recurring weekly macro schedule by assigning a template to days. This updates the DEFAULT schedule that applies to all future dates, not just a specific date override. First finds the template by name (from existing saved templates or from a recently created per-date template), then assigns it to the specified days of the week. Args: template_name: Name of a saved macro target template (e.g. "Retatrutide GI-Optimized", "Keto Rigorous"). days: Comma-separated day names or "all" (default). E.g. "Monday,Wednesday,Friday" or "all".
daystemplate_namerequiredList all saved macro target templates in Cronometer. Returns template names, IDs, and their macro values. Use this to find the template_name for set_weekly_macro_schedule.
Takes no parameters.
Create a new saved macro target template in Cronometer. Optionally assigns it to all days of the week as the recurring default. Args: template_name: Name for the new template (e.g. "Retatrutide GI-Optimized"). protein_grams: Protein target in grams. fat_grams: Fat target in grams. carbs_grams: Net carbs target in grams. calories: Calorie target in kcal. assign_to_all_days: If True, also set this as the recurring weekly schedule for all 7 days (default False).
caloriesrequiredfat_gramsrequiredcarbs_gramsrequiredprotein_gramsrequiredtemplate_namerequiredassign_to_all_daysGet fasting history from Cronometer. Returns all fasts (or fasts within a date range) with their status, names, recurrence rules, and timestamps. Args: start_date: Start date as YYYY-MM-DD (omit for all history). end_date: End date as YYYY-MM-DD (omit for all history).
end_datestart_dateGet aggregate fasting statistics from Cronometer. Returns total fasting hours, longest fast, 7-fast average, and completed fast count.
Takes no parameters.
Delete a fast entry from Cronometer. Use get_fasting_history first to find the fast_id. Args: fast_id: The fast ID to delete.
fast_idrequiredCancel an active (in-progress) fast while preserving the recurring schedule. Use get_fasting_history to find active fasts (is_active=true). Args: fast_id: The fast ID of the active fast to cancel.
fast_idrequiredGet the most recently logged biometric entries from Cronometer. Returns recent values for weight, blood glucose, blood pressure, heart rate, body fat, and other tracked biometrics.
Takes no parameters.
Add a biometric entry to Cronometer. Supported metric types: weight (lbs), blood_glucose (mg/dL), heart_rate (bpm), body_fat (%). Args: metric_type: One of 'weight', 'blood_glucose', 'heart_rate', 'body_fat'. value: The value in display units (lbs, mg/dL, bpm, %). entry_date: Date as YYYY-MM-DD.
valuerequiredentry_daterequiredmetric_typerequiredRemove a biometric entry from Cronometer. Use get_recent_biometrics to find biometric_id values. Args: biometric_id: The biometric entry ID (e.g. "BXW0DA").
biometric_idrequiredDownload Cronometer data and save locally as JSON + food-log.md. Downloads servings and daily summary data, saves JSON exports, and regenerates food-log.md. Output directory defaults to ~/.local/share/cronometer-mcp/ but can be overridden with the CRONOMETER_DATA_DIR environment variable. Args: start_date: Start date as YYYY-MM-DD (defaults to `days` ago). end_date: End date as YYYY-MM-DD (defaults to today). days: Number of days to look back if start_date not specified (default 14). diet_label: Optional diet label for the markdown header (e.g., "Keto Rigorous").
daysend_datediet_labelstart_dateCopy all diary entries from one date to another. Server-side operation that copies ALL entries (food, exercise, notes, biometrics) from source to destination. Additive — does not remove existing entries on the destination date. Args: source_date: Date to copy FROM as YYYY-MM-DD. destination_date: Date to copy TO as YYYY-MM-DD.
source_daterequireddestination_daterequiredMark a diary day as complete or incomplete. Args: date: Date to mark as YYYY-MM-DD. complete: True to mark complete, False to mark incomplete.
daterequiredcompleteList all recurring food entries. Returns all repeat items configured in Cronometer, including their food name, quantity, measure, diary group, and which days of the week they repeat on.
Takes no parameters.
Add a recurring food entry that auto-logs on selected days. Quantity is in default servings for the food (e.g., for coffee where the default serving is 1 cup, quantity=12 means 12 cups). Use search_foods to find food_id and food_source_id. Args: food_id: Numeric food ID from search_foods results. food_source_id: Food source ID from search_foods results. quantity: Number of default servings. food_name: Display name for the food. diary_group: Diary group name (case-insensitive) or 0-based index. Names are user-configured — call list_diary_groups to see this account's groups. Defaults to a time-of-day choice among enabled groups if omitted. days_of_week: Comma-separated day numbers (0=Sun, 1=Mon, ..., 6=Sat), or "all" for every day (default), or "weekdays", or "weekends".
food_idrequiredquantityrequiredfood_namerequireddiary_groupdays_of_weekfood_source_idrequiredDelete a recurring food entry. Use get_repeated_items to find the repeat_item_id. Args: repeat_item_id: The ID of the repeat item to delete.
repeat_item_idrequired90% 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.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
pip install cronometer-mcpgit clone https://github.com/cphoskins/cronometer-mcp.gitcd cronometer-mcppip install -e .export CRONOMETER_USERNAME="[email protected]"export CRONOMETER_PASSWORD="your-password"{ "mcpServers": { "cronometer": { "command": "cronometer-mcp", "env": { "CRONOMETER_USERNAME": "[email protected]", "CRONOMETER_PASSWORD": "your-password" } } }}{ "mcpServers": { "cronometer": { "command": "cronometer-mcp", "env": { "CRONOMETER_USERNAME": "[email protected]", "CRONOMETER_PASSWORD": "your-password" } } }}{ "command": "/path/to/venv/bin/python", "args": ["-m", "cronometer_mcp.server"]}docker run --rm -p 8000:8000 \ -e [email protected] \ -e CRONOMETER_PASSWORD=your-password \ -e CRONOMETER_TRANSPORT=streamable-http \ -e CRONOMETER_HOST=0.0.0.0 \ -e CRONOMETER_ALLOWED_HOSTS=your-server:8000 \ python:3.12-slim sh -c "pip install -q cronometer-mcp && cronometer-mcp"{ "mcpServers": { "cronometer": { "type": "http", "url": "http://your-server:8000/mcp" } }}export CRONOMETER_DATA_DIR="/path/to/your/project/data/cronometer"from cronometer_mcp import CronometerClient
client = CronometerClient( gwt_permutation="NEW_PERMUTATION_HASH", gwt_header="NEW_HEADER_VALUE",)from datetime import date, timedeltafrom cronometer_mcp import CronometerClient
client = CronometerClient() # reads from env vars
# Get today's food logfoods = client.get_food_log()
# Get last 7 days of daily summariesstart = date.today() - timedelta(days=7)summaries = client.get_daily_summary(start)
# Raw CSV exportcsv_text = client.export_raw("exercises", start, date.today())
# Copy a day's diary entriesclient.copy_day(date(2026, 3, 1), date(2026, 3, 8))
# Add a recurring food entry (every weekday)client.add_repeat_item( food_source_id=12345, measure_id=0, # universal gram-based measure quantity=200, food_name="Oatmeal", diary_group=1, # 0-based wire index; 1 == Breakfast on a default account days_of_week=[1, 2, 3, 4, 5],)
# Diary groups are user-configured - check what this account actually hasfor g in client.diary_groups: print(g["wire_index"], g["name"], g["enabled"])
# Log a biometricclient.add_biometric("weight", 218.5, date.today())