Health Export MCP vs Iposignal
A side-by-side look at the Health Export MCP and Iposignal MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Health Export MCP for monitoring work as a local process; choose Iposignal for monitoring over a hosted endpoint. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
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.
Choose Iposignal when
- You need dedicated capabilities in the Monitoring domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
get_ipo_overview, lookup_companies_with_financials, get_ipo_pipeline.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Monitoring | Monitoring |
| Quality signal | 65/100 · Great | 55/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Remote HTTP/SSE |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | HEALTH_DATA_DIR | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 6 | 0 |
| Directory activity | 4 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 14 | 10 |
| Full listing | View Health Export MCP | View Iposignal |
Tools & capabilities
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
Iposignal tools 10
get_ipo_overviewFREE. The public facts of an IPO: company, ticker, CIK, exchange, listing date, shares offered, price range, final offer price when the deal has priced, and gross proceeds. Use it to identify a deal before buying the full profile with get_ipo_snapshot. Provide exactly one of companyId, symbol, or cik.lookup_companies_with_financialsFREE. Directory of companies we hold SEC iXBRL financial statements for, optionally filtered by ticker or company name. Returns ticker, company, CIK, latest reported period and pre/post-IPO period counts — use it to find which tickers get_company_financials can return. Paged: limit (default 200, max 500) and offset; the response carries total and nextOffset (null on the last page).get_ipo_pipelineFREE. The US IPO pipeline: operating companies that have filed with the SEC but are not trading yet (status upcoming), or deals that were withdrawn or postponed. Each row has company, ticker when assigned, CIK, exchange, expected trading date when one is scheduled, the date of the latest status change, price range, shares offered, Nasdaq's deal size, and a link to the latest SEC filing. Status is the one the iposignal.xyz calendar shows, so SPACs and other vehicles are excluded. Use it to see what is coming to market or what was pulled; follow up with get_ipo_filings for one company's filing history or get_ipo_snapshot for the full deal profile. Arguments: status (upcoming, withdrawn or postponed; default upcoming), since as YYYY-MM-DD for withdrawn/postponed (default one year ago), limit (default 100, max 500). Upcoming deals sort by expected date, undated last.get_ipo_filingsFREE. One company's SEC filing timeline as we hold it, newest first: form type (S-1, S-1/A, F-1, F-1/A, EFFECT, 424B4, RW, 8-K, ...), filing date, and the link to the document on sec.gov. Use it to follow a registration from first S-1 through amendments to the final prospectus, or to confirm a withdrawal (RW). Covers the filings our SEC syncs collected for the company, not every filing it ever made. Provide exactly one of companyId, symbol, or cik.get_ipo_snapshotRetrieve a complete IPO company profile — deal terms, pricing range, expected market cap, SEC registration and prospectus details, offering structure, lifecycle timeline, and IBKR indicative borrow fee rate when available. When available, includes AI-generated research with valuation models, competitor benchmarking, underwriter ratings, board analysis, and risk factors. Provide exactly one of companyId, symbol, or cik. PREMIUM: paid per call over x402 (USDC on Base); an unpaid call returns the payment terms, and a not-found is never charged. Same data and price as the HTTP endpoint /api/agent/ipo/{id} or /api/agent/ipo/by-symbol/{symbol}.get_company_financialsRetrieve full SEC iXBRL financial statements for a company we cover, pre- and post-IPO, with derived margins, growth, leverage and return ratios per period. Interim periods carry annualized figures alongside the reported ones. Provide a symbol. PREMIUM: paid per call over x402 (USDC on Base); an unpaid call returns the payment terms, and a not-found is never charged. Same data and price as the HTTP endpoint /api/agent/financials/by-symbol/{symbol}.get_company_metricsGet live valuation metrics for any US-listed company (not just IPOs), computed from primary sources: SEC XBRL companyfacts TTM fundamentals (revenue, net income, EBITDA, debt, cash, shares) plus the latest market close. Returns multiples (P/E, P/S, EV/Revenue, EV/EBITDA), derivations (PEG, earnings/sales/EBITDA yields, net-debt/EBITDA), margins, and YoY growth — the same data IPOSignal's valuation pipeline uses for peer benchmarking, with the computation convention stated in the response. Provide exactly one of symbol (any SEC-mapped ticker) or companyName (resolves Nasdaq/NYSE listings). PREMIUM: paid per call over x402 (USDC on Base); an unpaid call returns the payment terms, and a not-found is never charged. Same data and price as the HTTP endpoint /api/agent/company-metrics.get_ipo_sentimentAccess IPOSignal's proprietary market sentiment score — a daily signal quantifying how well recent IPOs are being received by investors. Ranges from -100 (extreme bearish) to +100 (extreme bullish) with trend data for the last N days. Use it to identify favorable IPO windows, time investment entries, and assess overall market appetite for new listings. PREMIUM: paid per call over x402 (USDC on Base); an unpaid call returns the payment terms, and a not-found is never charged. Same data and price as the HTTP endpoint /api/agent/ipo-sentiment.get_ipo_social_sentimentGet IPOSignal's X/Twitter social-sentiment reading for a specific IPO — an aggregate of how investors are discussing the stock on X, scored from -1 (bearish) to +1 (bullish) with a label, post tallies, and a one-line summary. The reading is taken once, before listing, and not refreshed: `ageDays` says how old it is and `reliable` is false when too few posts back it. Returns the aggregate signal only, not the underlying posts. Provide exactly one of companyId, symbol, or cik. PREMIUM: paid per call over x402 (USDC on Base); an unpaid call returns the payment terms, and a not-found is never charged. Same data and price as the HTTP endpoint /api/agent/social-sentiment.get_ipo_eventsDated IPO events across all US IPOs in a window: lock-up expiries (with lock-up length), quiet-period expiries, and listings with offer price, first-day open and close, first-day pop and close return versus the offer, and lead managers. Use it to find upcoming lock-up expiries (supply overhang), quiet-period ends (analyst initiations) or how recent deals traded on day one. Arguments: from and to as YYYY-MM-DD (default today to today + 30 days, at most 366 days), types as a subset of lockup_expiry, quiet_period_expiry, listing (default all). PREMIUM: paid per call over x402 (USDC on Base); an unpaid call returns the payment terms, and an empty window is never charged. Same data and price as the HTTP endpoint /api/agent/ipo-events.
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.
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"
}
}
}
}
Iposignal
{
"mcpServers": {
"iposignal": {
"url": "https://iposignal.xyz/api/mcp"
}
}
}
Frequently asked questions
Health Export MCP is categorized under Monitoring and uses a local stdio subprocess. Iposignal belongs to Monitoring and uses a remote HTTP/SSE transport. Pick Health Export MCP for monitoring work and Iposignal 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.
Health Export MCP is listed as free. Auth: no auth required. Iposignal has no declared pricing — check the project's own site. 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 io-github-philipad-health-export-mcp and iposignal as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Health Export MCP has a quality signal of 65/100 (Great) with 4 views, 0 installs and 6 GitHub stars. Iposignal has 55/100 (Good) with 0 views, 0 installs and 0 GitHub stars.