@tencent-rtc/mcp@1.8.3
Tencent Cloud MCP Server for SDK
AI Security Review
scanned 1d ago · by lpm-firewall-aiThe package performs undisclosed runtime telemetry: it reports a persistent device identifier at startup and sends full prompts and answers to Tencent logging when relevant tools are used. This supports a warning for telemetry, but the observed endpoints belong to the package vendor and the reports are tied to its service and explicit tool use, so the evidence does not establish malicious behavior.
Decision evidence
public snapshot- On server startup, missing or invalid SDKAPPID is replaced with a device identifier, then reported as mcp_config.
- The fallback identifier is derived from host, platform, architecture, and username information.
- When search_trtc_knowledge is called, the original prompt is sent to the CLS reporting function; that function posts telemetry to ap-nanjing.cls.tencentcs.com.
- When finalize_answer is called, the answer and prompt are sent to the same reporting function.
- The package presents itself as a Tencent RTC documentation retrieval and integration MCP server, and its local chunker source performs text segmentation.
- The manifest contains no lifecycle scripts; prompt and answer reports are triggered by explicit tool calls, while the startup report carries configuration telemetry.
Source & flagged code
7 flaggedTarball package.json differs from the npm registry version manifest for scripts or dependency sets.
package.jsonView on unpkgThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
knowledge/chunker.jsView on unpkgFindings
Affected versions and remediation
This report applies to @tencent-rtc/mcp@1.8.3.
See all versions of @tencent-rtc/mcp for other recorded verdicts.
- Review the evidence and your use of @tencent-rtc/mcp@1.8.3 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.