# `com.dropwatchhq/health-intel` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/com.dropwatchhq/health-intel
- JSON: https://anlyon.dev/api/v1/servers/com.dropwatchhq/health-intel
- Version: 1.0.0 (active)
- Publisher: com.dropwatchhq (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T17:54:22.177Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Healthcare provider & compliance intel: NPPES lookup, OIG/SAM exclusion screening, FDA enforcement.
```

Scanned 2026-10-21T19:14:08.493Z over streamable-http.

**4 tools: 1 change things and 3 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 1 | ask |
| Only reads | read | 3 | allow |

## Findings

No check matched anything in these tool definitions.


## Changes things (1)

Creates or changes something that can be changed back. Claude Code: ask.

### `screen_exclusion`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Screen a provider/organization against the federal exclusion lists (HHS-OIG LEIE, and SAM.gov if configured). NPI match is exact; name match is flagged and identity-cautious. Returns sourced findings + a disclaimer. Facts, never an allegation.
```

## Only reads (3)

Looks things up and changes nothing. Claude Code: allow.

### `fda_enforcement`

- The description's first verb is "return": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Return recent FDA enforcement/recall actions tied to a device/drug firm (openFDA). A manufacturer-risk layer for procurement and payor teams.
```

### `new_exclusions`

- The description's first verb is "return": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Return providers newly added to the OIG-LEIE exclusion list, optionally scoped by state and/or specialty. The credentialing / payment-integrity alert feed.
```

### `provider_lookup`

- The name "provider_lookup" says "lookup": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Look up US healthcare providers from the public CMS NPPES registry by NPI, or search by specialty + state (+ optional name/city). Returns NPI, name, specialty, license, location, and an OIG-LEIE exclusion flag on each. Public data only — no PHI.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `health-intel`:

```json
{
  "permissions": {
    "allow": [
      "mcp__health-intel__provider_lookup",
      "mcp__health-intel__new_exclusions",
      "mcp__health-intel__fda_enforcement"
    ],
    "ask": [
      "mcp__health-intel__screen_exclusion"
    ],
    "deny": []
  }
}
```