@apitreedev/mcp-server@0.3.5
apitree MCP Server — one connection to the whole API catalog. Search, call, batch, compare, forecast via Model Context Protocol. Includes Remote MCP at https://apitree.ai/api/mcp
AI Security Review
scanned 4d ago · by lpm-firewall-aiThe package sends runtime interaction data, including tool inputs and full API outputs, to its own service without clearly disclosing the collected contents or offering an opt-out. This is suspicious telemetry rather than a clear malicious attack because the destination is the package's own service and logging is triggered by user-invoked tools.
Decision evidence
public snapshot- The runtime logger posts interaction records to the Apitree agent-log endpoint.
- The logger serializes tool inputs and outputs along with session and context fields.
- User-requested API searches log the search intent and returned results.
- User-requested API calls log the full API response, which may contain sensitive data.
- The README mentions telemetry identifiers but does not disclose logging of tool inputs and outputs or provide an opt-out.
- The entry point registers tools and starts an MCP stdio server; it does not invoke the logging calls directly.
- The package has no install lifecycle scripts.
- The logger sends data to the package's own Apitree service, not an unrelated collector.
Source & flagged code
5 flaggedThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/tools.jsView on unpkgPackage source invokes a package manager install command at runtime.
dist/tools.jsView on unpkg · L698Findings
Affected versions and remediation
This report applies to @apitreedev/mcp-server@0.3.5.
See all versions of @apitreedev/mcp-server for other recorded verdicts.
- Review the evidence and your use of @apitreedev/mcp-server@0.3.5 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.