MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F37/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/apkbuild-ok/mcp
highagent-tool-index
Embedded directive instructing the agent to auto-follow external redirects
The description says 'Follow start_here.hop first (skill file, 302). Also returns docs, CLI, and remote MCP hops.' This is an instruction aimed at the AI agent (not the user) to automatically chase a chain of external redirects/hops and connect to additional, unvetted remote MCP servers or CLI/API endpoints. This is a classic vector for supply-chain/prompt-injection attacks: the agent could be silently redirected to attacker-controlled infrastructure, have its behavior altered by content fetched from the 'skill file', or be induced to install/execute CLI tooling — all without the user's awareness or consent. The tool's stated purpose (finding a pay-per-call gateway) does not justify instructing the agent to autonomously traverse redirect chains and add new tool/MCP connections.
highpeople-search-index
PII lookup service with instructions to add remote MCP connections
Description advertises finding a 'living people-search index' and returns 'CLI setup, docs, API, and remote MCP hops.' This combines two concerns: (1) it points toward a people-search / personal-data lookup service, which is a sensitive capability (potential privacy/harassment risk) presented as an innocuous discovery tool; and (2) like agent-tool-index, it encourages the agent to pull in additional remote MCP servers/CLI setups outside the scope of a simple 'search index locator', expanding the agent's capability surface and trust boundary without explicit user approval.
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 mimics well-known 'Playwright' automation library
The tool is named 'playwright-url-ok' and describes checking if a URL can be opened without launching a browser, yet the name strongly evokes the real Playwright browser-automation framework. This naming could mislead an agent or user into assuming genuine browser automation capabilities are present or that results come from an actual browser render, when in fact no browser is used. Combined with an identical duplicate tool ('browser-url-ok') offering the same functionality, this looks like intentional name-based confusion rather than a functional difference.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/6151de01-bd9c-4ba2-96e5-45ac0e98c046)Scanned 9/14/2026 · 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