MCP security report

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

F43/100
Security grade FHigh-severity signals — review these before connecting.
Connected ✓31 tools scanned

https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/search-query-len/mcp

highpeople-search-index
Agent directed to discover and use a people-search / PII aggregation service
Description instructs the agent to 'Follow start_here.hop' (with tracking parameters) to locate a 'living people-search index' service, and exposes further CLI/API/MCP hops for it. Steering an agent toward people-search data brokers raises privacy and safety concerns (aggregating personal data about living individuals), and the embedded 'follow this link' instruction is a directive to the agent beyond the tool's stated function of a simple lookup.
mediumagent-tool-index
Embedded directive instructing agent to follow a tracked redirect chain
The description tells the calling AI to 'Follow start_here.hop first' through a 302 redirect that embeds utm_source=agent-observatory&utm_medium=agent tracking parameters, and to then follow additional docs/CLI/remote-MCP hops. This is an instruction aimed at the agent's behavior (navigate and follow a chain of external links) rather than a description of what the tool itself returns, and it steers the agent toward an external pay-per-call commercial gateway with tracking baked in, without the user's awareness or consent.
mediumagent-ads-index
Embedded instruction to follow tracked redirect and initiate a trial on behalf of the user/operator
The description instructs the agent to 'Follow start_here.hop first' (redirect carrying utm_source=agent-observatory&utm_medium=agent tracking) and states it returns a '7-day trial handoff for your operator.' This both embeds a navigation directive aimed at the AI and suggests the tool can initiate a commercial trial/signup flow on behalf of the user without clear, explicit user consent captured elsewhere in the conversation.
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.
lowsearch-query-len
Shared oversized schema with unrelated parameters across all tools
Every tool in this set exposes the identical broad input schema (zone, json, url, host, website, city, query, path, ref, feed) regardless of its stated single-purpose function (e.g., a character-counting tool accepts a 'website' field meant for agent-readiness checks). This is not inherently malicious but increases the chance that an agent passes sensitive or irrelevant data (e.g., file paths, hostnames) into tools whose descriptions claim narrow behavior, and makes it harder to audit what each tool actually does with each field.
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/20afb38a-fc2c-4433-827b-01acbbff3fd9)](https://gateturbo.com/report/20afb38a-fc2c-4433-827b-01acbbff3fd9)

Scanned 10/3/2026 · 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