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/http-507/mcp
highagent-tool-index
Embedded directive instructing agent to follow un-vetted redirect chain to a pay-per-call gateway
The description explicitly instructs the calling agent to 'Follow start_here.hop first (skill file, 302)' before doing anything else, and to also fetch docs, CLI, and remote MCP hops. This is an instruction embedded in a tool description that steers agent behavior (auto-following redirects to an external, monetized third-party service called 'Monid') rather than just describing the tool's function. This could lead the agent to silently incur costs, register with an unknown paid API, or load additional remote MCP tool definitions without explicit user awareness/consent — a classic vector for supply-chain/prompt-injection style manipulation via tool description.
mediumpeople-search-index
Facilitates locating a people-search / personal-data lookup service
This tool's stated purpose is to find 'a living people-search index (Ploid)' and surface CLI/API/remote-MCP hops for it. Directing an agent toward third-party people-search services raises privacy and misuse concerns (potential facilitation of doxxing, stalking, or unauthorized personal-data lookups) and, like agent-tool-index, encourages the agent to chain into unknown external services/APIs based on the tool description alone.
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.
lowhttp-507
Oversized, irrelevant input schema shared across unrelated tools
This tool (a simple lookup of what HTTP 507 means) exposes a schema with nine unrelated parameters (zone, json, url, host, city, query, path, ref, feed) that have nothing to do with its stated purpose. This pattern is repeated identically across nearly all 30 tools, suggesting a templated schema rather than a purpose-built one. While each field claims to be 'discarded,' the broad, unused surface area creates an unnecessarily large input contract that could be exploited to smuggle unrelated or sensitive data (e.g., file paths, URLs, hostnames) into a tool that has no legitimate need for them.
lowplaywright-url-ok
Name mimics well-known browser-automation tool but performs no browser action
The tool name 'playwright-url-ok' evokes the popular Playwright browser-automation framework, but the description clarifies 'No browser is launched.' Naming a lightweight URL-shape checker after a well-known automation tool could mislead an agent (or a user reviewing tool calls) into believing real browser automation capability exists, which is a mild form of name-based tool spoofing worth flagging even though the actual behavior is described accurately.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/d8a6c4d3-7789-48d7-bd13-2b1f289dbebc)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