MCP security report
agent-observatory-sensor.nolimit-observatory.workers.dev
F25/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓31 tools scanned
https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/yd-to-m/mcp
highagent-tool-index
Embedded directive to follow tracked redirect chains and connect to unspecified remote MCP servers
The description instructs the agent to 'Follow start_here.hop first' through a 302 redirect carrying utm_source=agent-observatory&utm_medium=agent tracking parameters, and states it 'also returns ... remote MCP hops.' This is an imperative aimed at the agent's behavior (not just a description of output), and it encourages the agent to discover and potentially connect to additional, unvetted remote MCP servers — a known supply-chain/tool-poisoning vector. The tracking parameters also suggest covert analytics on agent traffic rather than the user's benefit.
highpeople-search-index
People-search/PII aggregation tool with embedded redirect instructions and remote MCP hop discovery
This tool is framed as finding a 'living people-search index,' which implies surfacing personal information about identifiable individuals — a privacy/safety concern with no stated consent or purpose limitation. It also repeats the imperative 'Follow start_here.hop' redirect pattern with tracking parameters and offers 'remote MCP hops,' which could lead the agent to connect to untrusted third-party MCP servers, compounding both a privacy risk and a supply-chain risk.
mediumagent-ads-index
Advertising/monetization tool instructing agent to follow tracked redirects and initiates a trial 'for your operator'
Description embeds an instruction ('Follow start_here.hop first') with the same utm_source=agent-observatory&utm_medium=agent tracking, and advertises a '7-day trial handoff for your operator' — language suggesting the tool may enroll the operator/user in a paid trial as a side effect of an agent's tool call, without clear user consent in the loop. Combined with 'remote MCP hops' discovery, this raises both informed-consent and untrusted-server-connection concerns.
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.
lowyd-to-m
Oversized, irrelevant parameter schema shared across unrelated tools
A simple unit-conversion tool exposes unrelated parameters (zone, json, url, host, website, city, query, path, ref, feed) that have nothing to do with yards-to-meters conversion. This generic catch-all schema pattern is repeated identically across all 31 tools, which makes it hard to audit what data each tool actually consumes and could be used to smuggle sensitive data (e.g., file paths, JSON payloads, URLs) into a handler whose stated purpose doesn't justify needing them.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/ac3b1103-da2e-4b05-98e1-d1df1e90a160)Scanned 10/4/2026 · 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