MCP security report

ex.tetrees.ai

C73/100
Security grade CA few things are worth a closer look before connecting.
Connected ✓26 tools scanned

https://ex.tetrees.ai/mcp

mediumexecute_client_extension
References secrets or data exfiltration
The tool text references credentials, environment variables, or sending data elsewhere. This can be legitimate, but review what this tool actually accesses.
mediumexecute_client_extension
Broad execution capability with external network/process access
This tool executes methods against user-configured HTTPS APIs, nested MCP servers, or local child processes with argument passthrough. While there is a write-confirmation gate ('APPROVE extensionId.methodId'), the breadth of what can be invoked (arbitrary HTTPS endpoints, arbitrary local processes) combined with arbitrary JSON arguments creates a large attack surface if extension configuration or arguments are influenced by untrusted pack content. Agents should confirm exact extension/method targets and argument contents with the user before every write call, and treat non-write calls with similar scrutiny since read-only network calls can still exfiltrate data.
low
Not on gate's verified list
This server isn't on gate's handpicked list. That's not necessarily bad, but there's no third-party signal about it — review its tools carefully.
lowrun_ai_pack
Local file contents sent to third-party model providers
The attachmentPaths parameter allows local files (TXT, MD, CSV, JSON, PDF, DOCX, etc.) to be read and transmitted to the selected model provider (OpenAI, Claude, Z.AI) for the run. This is disclosed behavior, but the agent should ensure the user is aware that local file contents are being sent to an external hosted inference provider, especially for packs that are not yet owned/audited (stateless base preview) or when using platform-funded (non-BYOK) inference where the platform operator may also have visibility into transmitted content.
Embed this badge

Show your MCP server’s security grade

MCP security grade C

Paste this into your README:

[![MCP security](https://gateturbo.com/badge/scan/2527ec37-1594-4fab-beaf-5ee695856d9b)](https://gateturbo.com/report/2527ec37-1594-4fab-beaf-5ee695856d9b)

Scanned 9/10/2026 · This is a point-in-time snapshot of the server’s public tools. Re-scan.

Connect this server safely with gate.

Continuous re-scans, drift alerts, per-tool allow/ask/block, and a log of every call.

Monitor it — free