MCP Server vs Health Export MCP
A side-by-side look at the MCP Server and Health Export MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose MCP Server for monitoring work over a hosted endpoint; choose Health Export MCP for monitoring as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose MCP Server when
- You need dedicated capabilities in the Monitoring domain.
- You prefer a remote HTTP/SSE transport.
- Its auth model fits you: API key required.
- You want tools like
thinkneo_check_spend, thinkneo_complete, thinkneo_read_memory.
Choose Health Export MCP when
- You need dedicated capabilities in the Monitoring domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
HEALTH_DATA_DIR. - You want tools like
get_mcp_status, list_metrics, get_health_metrics.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Monitoring | Monitoring |
| Quality signal | 56/100 · Good | 67/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | API key required | No auth required |
| Pricing | Freemium | Free |
| Required env vars | None listed | HEALTH_DATA_DIR |
| Verified owner | Community listing | Community listing |
| GitHub stars | 3 | 8 |
| Directory activity | 2 views 0 installs 0 upvotes | 9 views 0 installs 0 upvotes |
| Tools | 68 | 14 |
| Full listing | View MCP Server | View Health Export MCP |
Tools & capabilities
MCP Server tools 68
thinkneo_check_spendCheck AI spend summary for a workspace, team, or project. Returns real cost breakdown by provider, model, and time period from the ThinkNEO AI gateway.thinkneo_completeRun a governed LLM completion through the ThinkNEO AI gateway. The request is authorized, classified, and policy-checked against your workspace governance BEFORE any provider is called — a blocked prompt never reaches the model. Tenant/workspace are derived from your API key.thinkneo_read_memoryRead Claude Code project memory files. Without arguments, returns the MEMORY.md index listing all available memories. With a filename argument, returns the full content of that specific memory file. Use this to access project context, user preferences, feedback, and reference notes persisted across Claude Code sessions.thinkneo_write_memoryWrite or update a Claude Code project memory file (.md). Persists project context, user preferences, feedback, and reference notes across Claude Code sessions. Filename must end in .md with lowercase alphanumeric characters. Path traversal is blocked. Requires authentication.Use this to persist project context, user preferences, feedback, and reference notes across Claude Code sessions. The filename must end in .md and contain only lowercase letters, digits, underscores, and hyphens (e.g. 'user_fabio.md', 'project_new_feature.md'). Path traversal is blocked.thinkneo_evaluate_guardrailEvaluate a prompt or text against ThinkNEO guardrail policies before sending it to an AI provider. Returns risk assessment, violations found, and recommendations. Requires authentication.thinkneo_checkFree-tier prompt safety check. Analyzes text for prompt injection patterns and PII (credit card numbers, Brazilian CPF, US SSN, email, phone, passwords). Returns a safety assessment with specific warnings. No authentication required.thinkneo_check_policyCheck AI governance policies including model access, budget limits, data controls, and agent governance from the ThinkNEO gateway.thinkneo_get_budget_statusCheck AI budget status including spend vs limit, forecast, and chargeback data from the ThinkNEO gateway.thinkneo_list_alertsList active alerts for budget, policy, SLA, and security from the ThinkNEO gateway.thinkneo_get_compliance_statusGet compliance status including framework coverage (EU AI Act, ISO 42001, NIST AI RMF, SOC 2) and governance assessments from the ThinkNEO gateway.thinkneo_provider_statusGet real-time health and performance status of AI providers routed through the ThinkNEO gateway. Shows latency, error rates, and availability. No authentication required.thinkneo_schedule_demoSchedule a demo or discovery call with the ThinkNEO team. Collects contact information and preferences. No authentication required.- +56 more on the listing page
Health Export MCP tools 14
get_mcp_statusHealth check: data source, how many metrics/workouts are available, which optional context files exist, and the most recent data date. Call this first to confirm the bridge is connected.list_metricsList every available Apple Health metric with its unit, day count, and date range. Use this to discover metric names before querying.get_health_metricsGet values for a metric (or all metrics) over an optional date range, with an aggregate (avg/sum/min/max/latest). The core data-retrieval tool. Every result carries a `coverage` block giving the metric's real firstDate/lastDate/days: check it before trusting a long window, and note that `aggregate` is always computed over the full range even when `points` are rolled up. Single-metric answers also list any logged point events inside the window as segmentBoundaries.get_trendsCompare the most recent N-day window against the prior N days for a metric: change, percent change and direction (up/down/flat). Also returns `daysAvailable` and `windowSatisfied`: if windowSatisfied is false the file does not hold enough history for the window you asked for, and the comparison is over less data than requested. Logged point events inside the compared span are listed as segmentBoundaries.compare_periodsCompare a metric between two arbitrary date periods (A vs B): each aggregate plus the change and percent change. Pass periodA/periodB explicitly, or pass anchor {eventId, days} to build both periods around a logged event (the before/after question, with the event day excluded from both sides).get_structured_exportReturn clean structured JSON for the chosen metrics/date range. Paginated: the result carries `nextCursor` when more metrics remain; pass it back as `cursor` for the next page. Prefer naming the metrics you need and a date range; calling it bare over a full history is a lot of data.get_intradayThe current hour-by-hour window from the iOS app's HOURLY automations (health-intraday.json, app 1.4+): each metric's hourly points plus its latest value. The file is REPLACED on every hourly run, so this is a live within-day view, not history; use get_health_metrics for day-level questions. Returns available:false with setup guidance when no hourly automation has delivered yet.query_health_dataNatural-language convenience: pass a question and get routed structured results. Prefer the specific tools above when you can, and call list_metrics first to see how much history exists, since this tool answers over whatever the file holds.list_eventsLogged context events from health-events.json: medication starts, habit changes, doctor visits, life events, shift blocks, episodes, travel, and any type a newer app adds. Optional {type, tag, start, end} filters; a range event matches a window it overlaps. Sorted ascending by date. Returns available:false when the file was never exported; absence means nothing was exported, not that nothing happened.get_profileThe context fields the user explicitly opted in to sharing (health-profile.json): conditions, medications, goals, allergies, notes. Returns the fields plus a presentFields list. An absent field was withheld by the user or never enabled; absence must never be read as "none".get_workoutsQuery the workouts cache with {activityType (a name like Running, or a raw HealthKit id like 37), start, end} filters and pagination ({limit} default 50 max 200, {cursor} from a previous nextCursor). Records are returned exactly as stored, including the newer optional keys (avgHeartRate, maxHeartRate, running dynamics, cycling power, intervals, hasRoute) when the app exported them; older caches simply lack those keys and nothing is fabricated. Also returns summary {count, byActivityType} over everything that matched.get_sleep_sessionsClustered sleep sessions from health-sessions.json with {start, end, day} filters. Sessions are attributed to the WAKING day, matching the daily cache's sleep_analysis, so the two surfaces never disagree; a split night appears as multiple sessions with the same day, returned as-is. Timestamps carry the local UTC offset at the time of the sample.- +2 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
MCP Server
{
"mcpServers": {
"thinkneoai-mcp-server": {
"url": "https://mcp.thinkneo.ai/mcp"
}
}
}
Health Export MCP
{
"mcpServers": {
"io-github-philipad-health-export-mcp": {
"command": "npx",
"args": [
"-y",
"health-export-mcp"
],
"env": {
"HEALTH_DATA_DIR": "YOUR_HEALTH_DATA_DIR_HERE"
}
}
}
}
Frequently asked questions
MCP Server is categorized under Monitoring and uses a remote HTTP/SSE transport. Health Export MCP belongs to Monitoring and uses a local stdio subprocess. Pick MCP Server for monitoring work and Health Export MCP for monitoring.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
MCP Server is listed as freemium — a free tier with paid plans. Auth: api key required. Health Export MCP is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add thinkneoai-mcp-server and io-github-philipad-health-export-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, MCP Server has a quality signal of 56/100 (Good) with 2 views, 0 installs and 3 GitHub stars. Health Export MCP has 67/100 (Great) with 9 views, 0 installs and 8 GitHub stars.