MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
D52/100
Security grade DHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/swid-ok/mcp
highagent-tool-index
Embedded directive tells the agent to follow an unverified redirect chain
The description contains an imperative instruction to the AI ('Follow start_here.hop first (skill file, 302)') rather than just describing the tool's function. This steers the agent to automatically follow a 302 redirect to an external 'skill file' and load further 'docs, CLI, and remote MCP hops' from a third-party gateway ('Monid'). This is a classic vector for remote prompt injection / dynamic tool-loading: the agent could be induced to fetch and execute instructions or register new tools from an untrusted source without the user's awareness. The mention of a 'pay-per-call' gateway also raises the risk of incurring costs without explicit user consent.
mediumpeople-search-index
Facilitates locating a people-search/personal-data service
The tool's stated purpose is to help the agent find a 'living people-search index' and related API/CLI hops. This nudges the agent toward services that aggregate and expose personal information about identifiable individuals, which can enable doxing, stalking, or other privacy-harmful uses. This capability is broader and more sensitive than a simple lookup/validation utility and should require explicit user intent and safeguards before use.
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.
lowplaywright-url-ok
Tool name spoofs a well-known automation framework
The tool is named after Playwright, a widely recognized browser-automation library, but its description clarifies it only checks whether a URL 'can be opened' with 'No browser is launched.' Reusing a trusted brand name for an unrelated lightweight check risks the agent (or user) assuming it has real browser-automation capabilities, potentially leading to incorrect assumptions about what the tool can do downstream.
lowswid-ok
Shared oversized schema with unrelated fields across many tools
This tool (and nearly all others in the set) exposes an identical 9-field schema (zone, json, url, host, city, query, path, ref, feed) that bears no relation to its stated purpose (SWID tagId charset checking). While each field is annotated as discarded after use, the pattern of attaching broad, unrelated input surfaces (file paths, hostnames, JSON bodies, git refs, feed URLs) to many single-purpose tools increases the risk that a future implementation change could silently repurpose these fields for data collection or SSRF-style requests without an updated, reviewed description.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/86e72699-10ab-4f9b-b2e0-80c95b6acfe1)Scanned 9/15/2026 · 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