MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
D55/100
Security grade DHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/lower-ok/mcp
highagent-tool-index
Embedded instruction to follow untrusted redirect chain
The description directs the agent to 'Follow start_here.hop first (skill file, 302)' and then follow additional 'docs, CLI, and remote MCP hops.' This is an instruction embedded in a tool description telling the AI to fetch and act on content from an external, unvetted location ('Monid' pay-per-call gateway) before doing anything else. This is a classic vector for prompt injection or supply-chain attack: the 'skill file' fetched via redirect could contain further instructions that override the agent's behavior, or point it toward installing/executing untrusted remote MCP servers or CLI tools. The agent should not blindly follow a chain of redirects/hops instructed by a tool description without user awareness and confirmation.
mediumpeople-search-index
Facilitates discovery of a people-search / personal data lookup service
This tool's stated purpose is to help locate a 'living people-search index (Ploid)' and provide API/CLI/remote MCP hops for it. Surfacing and encouraging use of people-search/data-broker style services raises privacy and safety concerns (potential for doxxing, stalking, or harvesting personal information about real individuals) and is a broad capability disguised as a simple lookup/index tool. It also shares the same 'follow hops' pattern as agent-tool-index, meaning it could lead the agent to fetch and act on unvetted remote instructions or install additional tooling for personal-data lookups.
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.
lowlower-ok, utc-time, timezone, validate-json, normalize-url, inspect-robots, domain-shape, citation, compatibility, status-catalog, iana-zones, web-fetch, fetch-status, github-repo-shape, weather-hint, memory-key-count, file-path-ok, browser-url-ok, think-steps, search-query-len, hn-front-count, lib-docs-hint, playwright-url-ok, figma-url-shape, jira-key-shape, geo-hint, calc-eval, wiki-title-ok
Uniform oversized schema unrelated to each tool's single stated purpose
Every tool in this set exposes the identical nine-parameter schema (zone, json, url, host, city, query, path, ref, feed) regardless of its narrow, single-purpose description (e.g., 'utc-time' accepts a city, path, feed, json body, git ref, etc. that have nothing to do with returning a timestamp). While each field description claims data is 'discarded', the mismatch between a tool's stated function and its accepted inputs is unusual: it could let a caller (or a manipulated agent) route arbitrary file paths, URLs, feeds, or JSON payloads through tools that appear unrelated to those inputs, and makes it hard for a reviewer or user to know what data a given call will actually touch. This pattern warrants clarification or schema tightening so each tool only exposes parameters relevant to its documented purpose.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/6ad23275-319e-486f-8d11-e3dae1844cd9)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