MCP Risk

Scan report

ai.sendinel/mcp-server

This page reports an automated security scan of ai.sendinel/mcp-server (npm), scanned 2026-07-28. It rates trust (provenance, transport, known vulnerabilities, instruction integrity) as grade B and capability risk (what the tools can do) separately at high. It does not certify the server is safe to connect; it reports what could be checked from outside.

npm, scanned 2026-07-28, tool surface via package-source

B 81/100 Capability risk: High permalink

The grade rates trust: provenance, transport, known vulnerabilities and instruction integrity. Capability risk rates what the tools can do and is reported, not penalised – a server built to run shell commands is doing its job (Policy §2.4).

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as ai.sendinel/mcp-server. 1 finding
  • Registry entry: ai.sendinel/mcp-server ↗
FAIL Source repository is public and maintained §1.2

Claimed source repository does not exist (or is private).
WARN Published package is consistent and attested §1.3
Minor integrity gaps: package is only 25 days old; no npm provenance attestation. 6 findings
  • Package: @sendinel/mcp-server@1.0.4 ↗
  • Ecosystem: npm
  • Age: 25 days
  • Weekly downloads: 46
  • Repo field matches source repo: true
  • Build-provenance attestation: absent
PASS Tool surface is inspectable and proportionate §2.1–§2.4
Package source scanned. Capabilities detected: network-egress. Reported as capability risk (§2.4); whether each is essential to the server's stated purpose is §2.3 and remains a manual judgement. 2 findings
  • network-egress (outbound network calls): build/tools/sms.js
  • Detected capabilities: network-egress
PASS HTTPS-only endpoint §3.1
Endpoint uses HTTPS. 1 finding
  • Endpoint: https://sendinel.ai/mcp
PASS Authentication required §3.2
Server rejects anonymous requests and advertises its auth scheme. 1 finding
  • WWW-Authenticate: Bearer resource_metadata="https://sendinel.ai/.well-known/oauth-protected-resource"
UNVERIFIABLE OAuth protected-resource metadata published §3.3

Metadata endpoint unreachable: Too many subrequests by single Worker invocation. To configure this limit, refer to https://developers.cloudflare.com/workers/wrangler/configuration/#limits
PASS No known vulnerabilities (OSV.dev) §4.1

No advisories on record for @sendinel/mcp-server @1.0.4 (npm).
PASS Server-supplied instructions free of poisoning indicators §5.1–§5.4

No poisoning indicators found across 100 server-supplied text item(s).

Verify manually - the scoring model can’t judge these for you

  • §2.3 - Is the tool surface no broader than the server’s stated purpose requires?
  • §3.4 - For stdio servers: which environment credentials does it read, and are they scoped rather than org-wide tokens?
  • §6.1 - Cross this server’s capabilities with your already-connected servers: any read-capability × send-capability pairs need explicit sign-off.
  • §6.2 - Run the connecting agent with sandboxing and egress controls sized to the combined tool surface, not just this server’s.

Methodology: MCP Server Security Policy. Checks and scoring weights are open source. Unfamiliar term? See the glossary.