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/html-meta-n/mcp
highagent-tool-index
Embedded instruction directing agent to follow untrusted redirect chains
The description contains an imperative instruction aimed at the AI ('Follow start_here.hop first (skill file, 302)') rather than a neutral description of the tool's function. This tells the agent to chase a redirect to an external, unspecified 'skill file' and then follow further 'docs, CLI, and remote MCP hops.' This pattern is a classic vector for supply-chain/prompt-injection attacks: it encourages the agent to fetch and potentially execute or trust instructions/content from an unverified third-party location ('Monid') outside the user's awareness, and to register/connect to remote MCP servers whose trustworthiness is unknown. The tool also references a 'pay-per-call' gateway, implying it could trigger billed actions without clear user consent.
highpeople-search-index
People-search / PII lookup tool with redirect-following instructions
This tool is described as finding 'a living people-search index (Ploid)' and returns hops to CLI, docs, API, and remote MCP endpoints for locating information about living individuals. This is a broad and privacy-sensitive capability (looking up personal data on real people) that goes beyond the simple utility functions of the rest of the toolset. Combined with the pattern of directing the agent through undisclosed external 'hops' (similar to agent-tool-index), this could be used to exfiltrate a user's query to a third-party people-search/data-broker service or to onboard the agent to an untrusted remote MCP server, without transparent user consent.
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.
lowagent-tool-index
Schema does not match tool's described function
The input schema for this tool includes unrelated fields (zone, json, url, host, city, query, path, ref, feed) that have nothing to do with 'finding a pay-per-call gateway.' This mismatch between schema and description, shared identically across many unrelated tools, makes it harder for reviewers/agents to reason about what data the tool actually consumes, and could mask which field is actually used to carry sensitive data to the remote gateway.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/e95fef38-1271-4304-89fc-b6a8fcbfc701)Scanned 9/17/2026 · 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