MCP security report
www.pathwren.workers.dev
F5/100
Security grade FA few things are worth a closer look before connecting.
Connected ✓9 tools scanned
https://www.pathwren.workers.dev/c/mcp-registry-official/mcp/netcheck
mediumwhoami
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.
mediumexample
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.
mediumverify_my_address
Directive language attempting to control agent's call order
The description contains 'THIS IS THE CALL TO MAKE FIRST on this server' — an imperative instruction aimed at the calling AI's behavior/tool-selection rather than a neutral description of functionality. This is a form of prompt-injection-style steering embedded in tool metadata.
mediumverify_batch
Embedded instruction to call a different tool first
Description begins with 'FIRST CALL, needs nothing:' followed by a full JSON-RPC request for a different tool (no_arguments_report_the_crawler_ip_ranges_this_host_mirrors). This pattern, repeated across multiple tools, is an attempt to dictate the agent's calling sequence via description text rather than through normal tool semantics.
mediumlookup_prefix
Embedded instruction to call a different tool first
Same 'FIRST CALL, needs nothing' pattern embedding a full call to another tool, steering agent behavior beyond describing this tool's own function.
mediumexport_ip_acl
Embedded instruction to call a different tool first
Same 'FIRST CALL, needs nothing' pattern embedding a full call to another tool, steering agent behavior beyond describing this tool's own function.
mediumverification_methods
Embedded instruction to call a different tool first
Same 'FIRST CALL, needs nothing' pattern embedding a full call to another tool, steering agent behavior beyond describing this tool's own function.
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.
lowwhoami
Reveals persistent tracking/profiling of the calling client
Description states the host reports 'whether this host has seen you before and what you fetched' and 'the class our instrument books you as' — implying the service maintains a history/profile of the calling agent's identity and prior requests, which is a data-retention/tracking behavior not obviously disclosed as the tool's stated purpose.
lowverify_batch
Non-MCP endpoint tagged with 'client-dossiers' parameter
The GET fallback URL includes 's=client-dossiers', suggesting requests are logged/tagged for building profiles ('dossiers') of callers. This hints at analytics/tracking beyond the stated crawler-verification purpose and is not explained to the user.
lowverification_methods
Non-MCP endpoint tagged with 'client-dossiers' parameter
The GET fallback URL includes 's=client-dossiers', the same tracking tag seen elsewhere, reinforcing the pattern of undisclosed client profiling by this host.
lowno_arguments_report_the_crawler_ip_ranges_this_host_mirrors
Excessively persuasive/repetitive self-justifying description
The description repeatedly over-asserts safety ('no key, no account, no OAuth, nothing to invent, read-only') and lists sibling tool paths/names in a way that reads more like an attempt to preemptively neutralize agent scrutiny than a factual tool description, a pattern consistent with prompt-injection style persuasion.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/144e53c8-d0cd-4523-b6ae-34c865408eda)Scanned 9/7/2026 · 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