registry / send16-mcp / 0.5.9

send16-mcp@0.5.9

MCP server for Send16 — let AI agents send transactional & marketing email, manage contacts/audiences/segments, automations, templates, inbox, suppressions, and webhooks. 79 tools, stdio + hosted HTTP (mcp.send16.com), zero-DNS sandbox sender.

AI Security Review

scanned 19h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

User runs the binary with the `install` argument, or an MCP client invokes a tool.

Impact

Configured agent hosts gain Send16 email and contact-management capabilities; the installer persists the supplied API key in host configuration.

Mechanism

Explicit MCP host configuration mutation plus authenticated Send16 API calls.

Rationale

No concrete malicious chain was found, but the explicit installer mutates multiple AI-agent control surfaces and persists credentials. Per policy, this is a warn-level dangerous capability rather than a publish-blocking install-time hijack.

Evidence

package.jsondist/index.jsdist/install-4NVVSMNV.jsdist/install-GUE465UP.js

Network endpoints1

api.send16.com

Decision evidence

public snapshot

AI called this Suspicious at 91.0% confidence as Dangerous Capability with low false-positive risk.

send16-mcp@0.5.9

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code