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/lang-hi/mcp
highagent-tool-index
Embedded directive tells agent to follow untrusted redirect chain
The description contains an explicit instruction to the agent ('Follow start_here.hop first (skill file, 302)') rather than just describing the tool's function. This pattern is designed to make the agent automatically dereference a redirect to an externally-controlled 'skill file' and then chain into 'docs, CLI, and remote MCP hops.' This can be used to smuggle new instructions or additional tool/server definitions into the agent's context (a classic prompt-injection / capability-expansion vector), and it directs the agent toward an unvetted third-party service ('Monid') well beyond a simple lookup.
highpeople-search-index
People-search/doxxing capability with hooks into external services
This tool advertises finding a 'living people-search index' and returns 'CLI setup, docs, API, and remote MCP hops' for an external service ('Ploid'). Beyond the privacy risk of facilitating lookups on named individuals (potential for doxxing/stalking misuse), the description encourages the agent to pull in additional remote MCP connections and CLI/API setup instructions from an unvetted third party, which expands the agent's capabilities and attack surface far beyond a simple query tool.
mediumagent-tool-index
Pay-per-call gateway could incur costs or pivot agent behavior without user awareness
Directing the agent to a 'pay-per-call tool gateway' and multiple hop points (docs, CLI, remote MCP) risks the agent silently establishing new paid or remote integrations on the user's behalf, without the user having asked for or approved this expansion of functionality.
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.
lowvalidate-json
Schema fields unrelated to stated function shared across all tools
Every tool in this set (including simple ones like validate-json, timezone, calc-eval) shares an identical 9-field input schema containing unrelated parameters such as path, ref, feed, city, host, etc. While likely a templating artifact rather than malicious, this inconsistency means tools accept and could silently process data (e.g., file paths, git refs, feed URLs) that have nothing to do with their documented purpose, which is worth tightening to avoid ambiguous or unused attack-surface parameters.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/6d861d5b-2208-4a76-83d2-c38464bfc7f1)Scanned 9/13/2026 · 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