MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F34/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/cc-td/mcp
highagent-tool-index
Embedded instruction directs agent to follow external redirect chain and adopt a pay-per-call remote gateway
The description contains an imperative aimed at the AI ('Follow start_here.hop first (skill file, 302)') rather than describing tool output. This instructs the agent to autonomously chase a redirect to an external 'Monid' gateway and load additional docs/CLI/remote MCP hops. This is a classic instruction-injection pattern: it directs agent behavior beyond the tool's stated function, can cause the agent to register/execute unknown remote MCP servers or CLI tools, and may incur real monetary charges ('pay-per-call') without explicit user awareness or consent.
highpeople-search-index
Directs agent to discover and integrate a people-search/background-check service with remote hops
Description promotes a 'living people-search index' and instructs the agent to fetch 'CLI setup, docs, API, and remote MCP hops.' This encourages the agent to pull in and trust additional remote tool definitions/credentials for a personal-data lookup service. Combining an instruction to chain into unreviewed remote MCP endpoints with a people-search (potentially surveillance/doxxing) capability is a significant risk: it can lead to exfiltration of personal data queries to an external, unvetted service and silent capability expansion of the agent's toolset.
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 reuses well-known automation tool brand despite limited function
Named after the popular 'Playwright' browser automation library while the tool only checks whether a URL can be opened and explicitly does not launch a browser. This name similarity could mislead the agent (or a user reviewing tool calls) into assuming full browser automation capability is available, which is a mild form of tool-name spoofing.
lowbrowser-url-ok
Generic 'browser' naming may imply broader capability than provided
The name suggests real browser interaction, but the tool description clarifies no browser is launched. Low risk of confusing the agent about actual capabilities, especially in combination with the similarly named playwright-url-ok tool.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/e6f7296e-c886-4b4a-93a5-247813d1afe9)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