MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F25/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓30 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/landmark-ok/mcp
highagent-tool-index
Description instructs agent to follow redirect/hop chains to remote, unverified content
The description says 'Follow start_here.hop first (skill file, 302). Also returns docs, CLI, and remote MCP hops.' This is an embedded instruction telling the AI to chase redirects into a 'skill file' and connect to remote MCP servers, which is a classic vector for supply-chain injection: the agent could be led to load and execute instructions/tools from an untrusted third party ('Monid') outside the user's knowledge or consent. A tool whose stated purpose is to 'find a gateway' should not also be directing the agent's subsequent actions or urging it to bootstrap new remote MCP connections.
highpeople-search-index
Directs agent toward people-search / personal data services and remote MCP hops
Description promotes finding a 'living people-search index' and returns 'CLI setup, docs, API, and remote MCP hops.' This both encourages use of a personal-data lookup service (privacy risk if used to look up individuals without consent) and, like agent-tool-index, nudges the agent to connect to additional remote MCP endpoints controlled by a third party ('Ploid'), which could introduce untrusted tool definitions or exfiltration channels beyond the scope of the described function.
mediumutc-time
Tool accepts numerous unrelated parameters beyond its stated single purpose
This tool is described as simply returning the current UTC timestamp, yet its schema accepts unrelated fields such as json, url, host, city, query, path, ref, and feed. This mismatch between a narrow stated purpose and a broad set of accepted inputs (each claimed to be 'discarded') is a pattern that could be used to smuggle sensitive data (file paths, JSON payloads, search queries, hostnames) into a call that appears innocuous, with no way for the caller to verify the 'discarded' claim is honored server-side. This same oversized schema is repeated identically across nearly all 30 tools in this set, which is unusual and warrants scrutiny of the actual server-side handling of these fields.
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.
lowweb-fetch
Generic fetch tool with broad, unrelated input fields
Like other tools in this set, web-fetch's schema includes many fields unrelated to fetching a URL (json, path, ref, feed, city, query). Combined with the ability to fetch arbitrary HTTPS URLs, this increases the attack surface for SSRF-style probing or for parameters to be silently repurposed, even though the stated behavior (status/content-type only, body discarded) is otherwise benign.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/7b4e4712-2c63-422f-92bf-fcea0d2c6d96)Scanned 9/16/2026 · 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