# Uphealth Signal (npm · @uphealth/mcp-server)

The adaptive health-messaging engine for apps and agents. Federally-sourced. Not medical advice.

- Trust score: 61/100 (medium)
- Change this week: +16
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.uphealth.us`: 72/100, [markdown](https://verifymcp.io/servers/us-uphealth-mcp/mcp.md), [page](https://verifymcp.io/servers/us-uphealth-mcp/mcp)
- npm · `@uphealth/mcp-server`: 61/100 (this document), [markdown](https://verifymcp.io/servers/us-uphealth-mcp/uphealth-mcp-server.md), [page](https://verifymcp.io/servers/us-uphealth-mcp/uphealth-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@uphealth/mcp-server`
- Version: `1.1.5`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (121 of 123), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (121 of 123), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 11 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 65/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 926 tokens (~132/item across 7 items; 5 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 80% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add us-uphealth-mcp -- npx -y @uphealth/mcp-server
```

### Codex

```bash
codex mcp add us-uphealth-mcp -- npx -y @uphealth/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "us-uphealth-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@uphealth/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add us-uphealth-mcp --command npx --arg -y --arg @uphealth/mcp-server
```

### Hermes

```yaml
mcp_servers:
  us-uphealth-mcp:
    command: "npx"
    args: ["-y", "@uphealth/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "us-uphealth-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@uphealth/mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 60, +60)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100
- [functional] Licence: MIT

### 2026-08-01 (score 0, −20)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified

### 2026-07-31 (score 20, −7)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 27, +9)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 18, −27)

- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (5)

### `lookup_health_fact` (~157 tokens)

Zero setup — NO key required. Returns ONE already-public federal health fact, list, or tip for a question or topic (e.g. "high blood pressure", "sleep", "type 2 diabetes"), with its federal source (CDC / MedlinePlus / NIH) and a link to the public uphealth.me page. Free + rate-limited. For adaptive, patient-specific message sequencing — receptivity-scored cues + audience-safety verdicts over the full library of federally-sourced facts, lists & tips — get a free Discovery key at https://uphealth.us/signup

Input parameters:

- `q` (string, required): A health question or topic, e.g. "high blood pressure", "sleep", or "type 2 diabetes".

Output parameters:

- `attribution` (string): "Source: <agency> via Uphealth".
- `disclaimer` (string)
- `fact` (object): The single already-public federal message — a fact, list, or tip (see kind).
- `topic` (string): The matched topic's title.
- `upgrade` (object): The free-key upsell — adaptive sequencing lives behind a Discovery key.

### `create_patient_stream` (~347 tokens)

Create a Signal cued stream for one patient and get the first cue back synchronously. Every cue is federally-sourced, audience-safety-checked, and sequenced on the patient's prior response — so your agent never fabricates health content. Choose a template_id from the signal://catalog resource and pre-satisfy its required audience_tags + patient_context (clinical templates 422 without them). Display mode renders in your app: no PHI, no BAA. Each later cue MUST submit the prior message's feedback — the engine refuses to advance without it (the sequencing moat).

Input parameters:

- `attributes` (object): De-identified patient context. v1 accepts free-form jsonb; future templates will enforce schemas.
- `audience_tags` (array): Subset of the 14-tag B5/B6 schema. See list_sandbox_topics for sample topic labels.
- `delivery_mode` (string): v1 is Display-only; Deliver-mode unlocks at Per-Episode tier after BAA.
- `feedback_timeout_days` (integer)
- `idempotency_key` (string): Optional. Stripe-style create idempotency: a retried create with the same key returns the ORIGINAL stream instead of minting (and billing) a second one. Forwarded as the Idempotency-Key request heade…
- `template_id` (string, required): One of the live Signal templates. Read the signal://catalog resource for each template's required audience_tags + patient_context. On a production key a clinical template 422s if its required tags/co…

Output parameters:

- `_meta` (object): Legal/disclosure block returned on every 2xx (A1 §6.7).
- `first_cue` (object): A cued message plus its per-cue receptivity score and audience-safety verdict.
- `next_cue_eligible_at` (string|null)
- `rate_limit` (object): Discovery monthly cue-cap headroom. Absent on non-Discovery tiers (no cap).
- `state` (string)
- `stream_id` (integer): Persist this — every later cue/read references it.

### `get_next_cued_message` (~136 tokens)

Submit the patient's response to the prior cue and get the next one — federally-sourced, audience-safety-checked, and re-sequenced on that feedback. REFUSES WITHOUT PRIOR-MESSAGE FEEDBACK (the moat): the engine will not advance a stream blind, returning 409 if you skip it. response_action is one of the accepted cue vocabulary (see the signal://catalog resource). Same idempotency_key + same feedback returns the cached cue; conflicting feedback under the same key returns 409.

Input parameters:

- `feedback` (object, required)
- `stream_id` (integer, required): The stream_id returned by create_patient_stream.

Output parameters:

- `_meta` (object): Legal/disclosure block returned on every 2xx (A1 §6.7).
- `idempotent` (boolean): true when this is the cached result of a repeated idempotency_key.
- `message` (string)
- `next_cue` (object): A cued message plus its per-cue receptivity score and audience-safety verdict.
- `normalized_action` (string|null): null when the submitted response_action was a recognized value; otherwise the acknowledge-class value the well-formed-but-unrecognized action was folded to (forward-compat tolerance). Always present…
- `rate_limit` (object): Discovery monthly cue-cap headroom. Absent on non-Discovery tiers (no cap).
- `sandbox_exhausted` (boolean): Present + true when the sandbox subset is exhausted; no next_cue then.
- `state` (string)
- `stream_id` (integer)

### `read_stream_state` (~79 tokens)

Read a stream's current state, its current cued message, and event count. Read-only — does NOT advance the stream or consume a cue. Use it between feedback turns to inspect where a patient is in their federally-sourced, audience-safety-checked sequence.

Input parameters:

- `stream_id` (integer, required): The stream_id returned by create_patient_stream.

Output parameters:

- `_meta` (object): Legal/disclosure block returned on every 2xx (A1 §6.7).
- `current_cue` (object|null)
- `events_count` (integer)
- `next_cue_eligible` (boolean)
- `rate_limit` (object): Discovery monthly cue-cap headroom. Absent on non-Discovery tiers (no cap).
- `state` (string)
- `stream_id` (integer)
- `template_id` (string)

### `list_sandbox_topics` (~75 tokens)

List the curated sandbox topic labels that define the free Discovery corpus — every topic federally-sourced and audience-safety-checked. Use it to preview what content domains exist before creating a stream. Does NOT enumerate messages — the corpus stays internal. For the full live template catalog + gating contract, read the signal://catalog resource.

Output parameters:

- `_meta` (object): Legal/disclosure block returned on every 2xx (A1 §6.7).
- `template_id_for_sandbox` (string)
- `topic_labels` (array)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/us-uphealth-mcp/uphealth-mcp-server#diagnostics

## Score history

- 2026-08-03: 61
- 2026-08-02: 60
- 2026-08-01: 0
- 2026-07-31: 20
- 2026-07-30: 27
- 2026-07-28: 18
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/@uphealth/mcp-server
- Socket report: https://socket.dev/npm/package/@uphealth/mcp-server
- Website: https://uphealth.us/docs/mcp-quickstart
- Changelog RSS feed: https://verifymcp.io/servers/us-uphealth-mcp/uphealth-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/us-uphealth-mcp/uphealth-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/us-uphealth-mcp/uphealth-mcp-server