MCP security report

agent-observatory-sensor.nolimit-observatory.workers.dev

F7/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓31 tools scanned

https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/league-km/mcp

highagent-tool-index
Embedded instruction to follow a tracked redirect chain
The description tells the agent to 'Follow start_here.hop first' through a 302 redirect carrying utm_source=agent-observatory&utm_medium=agent tracking parameters, and lists additional hops (docs, CLI, remote MCP) to follow. This is an instruction aimed at the AI's behavior rather than a description of the tool's function, directing it to autonomously traverse external links and carry tracking parameters, which can be used to attribute/monetize agent traffic or lead the agent to unreviewed third-party endpoints without the user's awareness.
highpeople-search-index
Instruction to auto-follow tracked redirects to a people-search service
Similar to agent-tool-index, this description instructs the agent to 'Follow start_here.hop' with tracking parameters and then surface a 'living people-search index.' Steering an agent toward locating and indexing a service for searching personal data on living individuals raises privacy/doxxing risk, and the embedded redirect-following instruction is an attempt to control agent navigation behavior outside the tool's stated purpose (an index lookup).
highagent-ads-index
Ad-network onboarding instructions embedded in tool description, including action on behalf of the operator
The description instructs the agent to follow a tracked redirect chain and explicitly mentions returning a '7-day trial handoff for your operator.' This frames the tool as a vehicle to enroll the human operator in a paid/trial service via agent action, which is a manipulation vector: it embeds marketing/onboarding instructions targeted at the AI rather than describing a narrow, bounded tool capability, and could result in the agent taking consequential actions (service signup) without clear 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.
lowleague-km
Oversized shared parameter schema unrelated to stated single-purpose function
Every tool in this set (league-km, utc-time, timezone, validate-json, etc.) shares an identical schema exposing unrelated parameters (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's narrow stated purpose. This suggests a single backend handler ingests many different data types (URLs, file paths, search queries, JSON bodies, git refs, feeds) under each tool call. While each field is individually described as 'discarded,' the broad, unified intake surface across dozens of nominally distinct tools is unusual and could be used to collect more data than any single tool's description implies; this pattern is repeated identically across all 31 tools and should be verified against actual server-side behavior.
Embed this badge

Show your MCP server’s security grade

MCP security grade F

Paste this into your README:

[![MCP security](https://gateturbo.com/badge/scan/457d8dcc-a026-49e5-bc96-d59e41b480ed)](https://gateturbo.com/report/457d8dcc-a026-49e5-bc96-d59e41b480ed)

Scanned 10/1/2026 · 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