ARPI MCP
SAFEgrade B · trust 86/100None
Overview
From the repository's own README, as read at the audited commit.
# ARPI MCPRemote MCP server by [ARPI Inc.](https://arpi.ai) — AI-powered ECG analysis with ARPI's ECG AI.Submit ECG images and receive AI-generated diagnosis reports directly from your MCP client.- **Endpoint:** `https://mcp.arpi.ai/mcp` (Streamable HTTP)- **Auth:** OAuth — the client is guided through login on first connection## Tools| Tool | Description ||------|-------------|| `authenticate` | Sign in to ARPI || `open_image_submission` | Start an ECG image submission || `submit_image_for_diagnosis` | Submit an ECG image for AI diagnosis || `fetch_diagnosis_reports` | Retrieve diagnosis reports || `list_available_capabilities` | List available analysis capabilities || `invoke_arpi_capability` | Invoke a specific analysis capability |## Installation### Claude Code```bashclaude mcp add --transport http arpi-mcp https://mcp.arpi.ai/mcp```Or via the plugin marketplace:```bashclaude plugin marketplace add arpi-ai/arpi-mcpclaude plugin install arpi-mcp@arpi-mcp```### Claude.ai / Claude DesktopSettings → Connectors → Add custom connector → `https://mcp.arpi.ai/mcp`### Other MCP clientsAny client supporting Streamable HTTP with OAuth can connect to `https://mcp.arpi.ai/mcp`.## Repository layoutThis repository contains registry/marketplace metadata only — the server itself is hosted by ARPI.- `server.json` — [official MCP Registry](https://registry.modelcontextprotocol.io) listing- `.claude-plugin/marketplace.json` + `plugins/arpi-mcp/` — Claude Code plugin marketplace## Support- Support: [email protected]'s ECG AI is a medical AI service. Diagnosis reports are for reference and do not replace professional medical judgment.
Details
- Source
- arpi-ai/arpi-mcp
- Transports
- streamable-http
- Tools
- Registered at runtime; the list could not be read from source.
- Stars
- 0 · pushed 66d ago
Trust audit
Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
streamable-http
Gates applied: no_behavioural_pass, no_license.
Audited 2026-09-13 · audit v0.4.0 · source sha 22e066a1bd1a · full audit: observations/trust-audit/mcp-server/arpi-ai__arpi-mcp.json · Report an issue or request a re-scan
Audit history
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-13 | 22e066a1bd1a | SAFE | B | 86 | source changed, verdict held |
Also audited
Servers with a similar trust profile.
Questions
What is the ARPI MCP MCP server?
None
Is ARPI MCP safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (86/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does ARPI MCP need?
No credential environment variables were found in its source, so it appears to need none.
How does ARPI MCP run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (22e066a1bd1a), read on 2026-09-13. The repository is watched and re-audited when it changes.
Provenance: OBSERVED · read 2026-09-13 · job trust-audit-2026-09-13