fitbit-googlehealth-mcp
This MCP server enables Claude to access and log Fitbit health data, including activity, sleep, heart rate, and nutrition, with the ability to log meals by analyzing photos through Claude's vision capabilities.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
tachibanayu24
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
get_daily_summarySteps, calories out, distance, heart rate zones (resting + zone minutes), active-minute bucket totals for a single day. Cached for 1 hour. NOTE: values for the current JST day can be unstable until Fitbit finalises aggregation (e.g. negative `sedentaryMinutes`, or a huge `caloriesOut` on the Out of …
get_activity_timeseriesDaily values of one activity metric across a date range. Useful for trending steps, distance, calories. Cached 1h.
get_exercise_listReturns recent exercise / activity log entries (runs, walks, workouts) in reverse chronological order.
get_body_logLogged weight and body fat entries across a date range. BMI is returned when Fitbit computed it. Cached 1h.
list_devicesLists Fitbit devices tied to the user (battery level, last sync time, model). Cached for 1 hour.
get_heart_rate_rangeDaily resting heart rate and time-in-zone for each day in the range. Cached 1h.
get_heart_rate_intradayTime-series heart rate for a single day at the requested resolution. 1sec is only reliable during logged exercises; 1min is best for all-day trends. Personal Fitbit apps have immediate intraday access. NOTE: Fitbit itself sometimes returns an empty or partial dataset even when heart-rate zone summar…
get_spo2Nightly SpO2 averages (min / avg / max) across a date range. Cached 1h.
get_respiratory_rateSleep-derived breathing rate per day, broken down by sleep stage when available. Cached 1h.
get_skin_temperatureOvernight skin-temperature delta relative to the user baseline. Only available on supported devices. Cached 1h.
get_hrvNightly HRV (daily RMSSD and deep-sleep RMSSD). Useful for recovery trending. Cached 1h.
get_cardio_fitnessVO2 max estimate from Fitbit. Returned as a range string (e.g. "45-49") or a numeric value depending on device. Defaults to today (JST). Cached 1h.
get_food_logMeals and water intake for the day: foods array, nutrition summary (calories/carbs/fat/fiber/protein/sodium/sugar), water total, and—when Fitbit has set one—a calorie goal. The `goals` field is omitted on days with no food entries. Defaults to today (JST). Cached 1h.
get_profileReturns the authenticated user profile: display name, dates, unit system, timezone, and averages. Cached for 1 hour.
get_sleepFitbit sleep logs (v1.2) for a date, including stage data (deep/light/rem/wake) when the device captured them. Defaults to today (JST). Cached 1h.
get_sleep_rangeFitbit sleep logs (v1.2) across a date range. Good for week-over-week comparisons. Cached 1h.
log_activityRecord a workout that Fitbit did not auto-detect. Provide either `activityId` (Fitbit activity catalog) or `activityName` + `manualCalories`. Duration must be in milliseconds.
delete_activity_logRemove a previously logged exercise by its logId (from log_activity output or from get_exercise_list[].logId).
log_weightRecord a weight reading. BMI is computed by Fitbit if a height is on file.
log_body_fatRecord a body-fat percentage reading (e.g. from a smart scale).
delete_weight_logRemove a previously logged weight entry by its logId (from log_weight output or from get_body_log.weight[].logId). Use this to undo a mis-typed or test reading.
delete_body_fat_logRemove a previously logged body-fat entry by its logId (from log_body_fat output or from get_body_log.fat[].logId).
log_foodlog_meal_photolog_waterRecord water consumption in millilitres for the given date.
delete_food_logRemove a previously logged food entry by its logId (from log_food or log_meal_photo output). Use this to undo a mistake.
delete_water_logRemove a previously logged water entry by its logId (from log_water output or from get_food_log.water.water[].logId).
save_meal_presetlist_meal_presetsReturn every meal preset saved on this MCP server, sorted by most-recently-updated. Call this first when the user says "X を記録して" to check if X is already a preset.
delete_meal_presetRemove a saved meal preset by name. Prior log entries are NOT affected.
log_presetlog_sleepRecord a sleep session that was not auto-detected. Duration is in milliseconds. Useful for nap logging or catch-up after forgetting to wear the device.
delete_sleep_logRemove a previously logged sleep entry by its logId (from log_sleep output or from get_sleep[].logId).
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
Vitest allows Remote Code Execution when accessing a malicious website while Vitest API server is listening
Hono JWK Auth Middleware has JWT algorithm confusion when JWK lacks "alg" (untrusted header.alg fallback)
hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard
Hono JWT Middleware's JWT Algorithm Confusion via Unsafe Default (HS256) Allows Token Forgery and Auth Bypass
FITBIT_CLIENT_IDexport =<your-client-id>FITBIT_CLIENT_SECRETexport =<your-client-secret>Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
33/33 tools missing one or more hints — get_daily_summary (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_activity_timeseries (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_exercise_list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +30 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
30/33 tool handlers declare input schemas (91%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
Only 0/33 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Production dependencies are patched
0 critical, 5 high severity in production deps — hono@4.7.0 (high), hono@4.7.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
3 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/tachibanayu24/fitbit-googlehealth-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check