# ingest_patient_record

Upload a patient record file (.txt, .csv, .pdf, .docx) or paste unstructured clinical text to extract a structured patient profile. The file is decoded, text is extracted, and Gemini LLM converts it into the same JSON format used by all PharmaGuard safety tools. The patient is stored in memory with an assigned ID for immediate use in safety checks. Supported formats: plain text, CSV, PDF (text-based), DOCX.

Agent View of the PolicyLayer registry record for `ingest_patient_record`. HTML page: https://policylayer.com/tools/nitrostack/ingest-patient-record

## Facts

- Tool: `ingest_patient_record`
- Server: Nitrostack (`nitrocloudofficial/nitrostack`) — https://policylayer.com/tools/nitrostack.md
- Homepage: https://github.com/nitrocloudofficial/nitrostack
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "ingest_patient_record",
    "arguments": {}
  }
}
```

## Why ingest_patient_record is rated Medium

Creates and stores patient records in system memory; reversible write with high sensitivity given medical data involved.

From the tool's own definition: "Upload patient record file, extract structured patient profile, patient stored in memory"

## Use case

AI agents use ingest_patient_record to create or update resources in Nitrostack, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nitrostack environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Nitrostack:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "ingest_patient_record": {
      "limits": [
        {
          "counter": "ingest_patient_record_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Nitrostack (696)

- `cancel_appointment` — Destructive — https://policylayer.com/tools/nitrostack/cancel-appointment.md
- `cancel_followup` — Destructive — https://policylayer.com/tools/nitrostack/cancel-followup.md
- `cancel_order` — Destructive — https://policylayer.com/tools/nitrostack/cancel-order.md
- `clean_temp_files` — Destructive — https://policylayer.com/tools/nitrostack/clean-temp-files.md
- `clear_icon_cache` — Destructive — https://policylayer.com/tools/nitrostack/clear-icon-cache.md
- `commit_transaction` — Destructive — https://policylayer.com/tools/nitrostack/commit-transaction.md
- `delete_account` — Destructive — https://policylayer.com/tools/nitrostack/delete-account.md
- `delete_chat_session` — Destructive — https://policylayer.com/tools/nitrostack/delete-chat-session.md
- `delete_document` — Destructive — https://policylayer.com/tools/nitrostack/delete-document.md
- `delete_message` — Destructive — https://policylayer.com/tools/nitrostack/delete-message.md
- `delete_project` — Destructive — https://policylayer.com/tools/nitrostack/delete-project.md
- `empty_recycle_bin` — Destructive — https://policylayer.com/tools/nitrostack/empty-recycle-bin.md
- `obsidian-delete-note` — Destructive — https://policylayer.com/tools/nitrostack/obsidian-delete-note.md
- `release_environment` — Destructive — https://policylayer.com/tools/nitrostack/release-environment.md
- `remove_policy_rule` — Destructive — https://policylayer.com/tools/nitrostack/remove-policy-rule.md
- `reset_demo` — Destructive — https://policylayer.com/tools/nitrostack/reset-demo.md
- `reset_demo_data` — Destructive — https://policylayer.com/tools/nitrostack/reset-demo-data.md
- `revoke_api_key` — Destructive — https://policylayer.com/tools/nitrostack/revoke-api-key.md
- `revoke_invite` — Destructive — https://policylayer.com/tools/nitrostack/revoke-invite.md
- `rollback_transaction` — Destructive — https://policylayer.com/tools/nitrostack/rollback-transaction.md
- `screen_fraud` — Destructive — https://policylayer.com/tools/nitrostack/screen-fraud.md
- `send_email` — Destructive — https://policylayer.com/tools/nitrostack/send-email.md
- `accept_offer` — Execute — https://policylayer.com/tools/nitrostack/accept-offer.md
- `advance_application` — Execute — https://policylayer.com/tools/nitrostack/advance-application.md
- `analyze_material_health` — Execute — https://policylayer.com/tools/nitrostack/analyze-material-health.md
- `analyze_video` — Execute — https://policylayer.com/tools/nitrostack/analyze-video.md
- `approve_action` — Execute — https://policylayer.com/tools/nitrostack/approve-action.md
- `audit_pizza_shops` — Execute — https://policylayer.com/tools/nitrostack/audit-pizza-shops.md
- `call_tool` — Execute — https://policylayer.com/tools/nitrostack/call-tool.md
- `chat_architect` — Execute — https://policylayer.com/tools/nitrostack/chat-architect.md
- …and 666 more: https://policylayer.com/tools/nitrostack.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=nitrostack · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/nitrostack