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/tiger-ok/mcp
highagent-tool-index
Embedded directive instructing agent to follow an external redirect chain
The description contains an imperative instruction aimed at the AI ('Follow start_here.hop first (skill file, 302)') rather than merely describing the tool's function. This steers the agent to automatically follow a redirect to an external, unverified 'skill file' and then to additional docs/CLI/remote MCP endpoints. This is a classic pattern for smuggling in follow-on instructions or pivoting the agent to attacker-controlled infrastructure without explicit user awareness or consent, especially since it references a 'pay-per-call' gateway that could incur costs or execute further actions.
highpeople-search-index
People-search capability with hidden expansion via remote MCP hops
This tool's stated purpose is to locate a service for searching information about living people, and its description explicitly returns 'CLI setup, docs, API, and remote MCP hops.' Combining a people-search/doxing-adjacent capability with an instruction-like pointer to additional remote MCP endpoints creates risk of privacy harm (facilitating searches on real individuals) and uncontrolled expansion of the agent's capabilities to unvetted external services.
mediumagent-tool-index
Encourages connecting to additional remote MCP servers
The tool advertises 'remote MCP hops' as part of its output, implying it can lead the agent to add or invoke other MCP servers. Expanding the agent's tool surface via a chain of hops discovered at runtime is a supply-chain risk: the user has not vetted these additional servers, and the agent could be induced to load new capabilities silently.
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.
lowtiger-ok
Schema exposes broad, purpose-mismatched input fields across many tools
Nearly all 30 tools share an identical, very broad input schema (zone, json, url, host, city, query, path, ref, feed) regardless of the tool's actual single-purpose function (e.g., a hex-length checker accepting a file 'path' or Git 'ref'). While each field claims to be 'discarded' after use, the mismatch between declared purpose and accepted parameters is unusual and could mask which fields are actually processed/retained versus which are decorative, making it harder for reviewers or agents to reason about actual data flow.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/5fa46cfb-5e56-47f7-9c83-83e9297b48c7)Scanned 9/15/2026 · 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