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/mime-toml/mcp
highagent-tool-index
Embedded directive instructs agent to auto-follow tracked redirect
The description contains an imperative command aimed at the AI ('Follow start_here.hop first') rather than just describing the tool's output. It also pre-attaches tracking parameters (utm_source=agent-observatory&utm_medium=agent) to a URL the agent is told to visit, and frames the destination as a 'pay-per-call tool gateway.' This steers the agent into visiting and potentially registering with an external monetized service without the user's explicit awareness or consent, and the attribution tags suggest the tool exists to funnel agent traffic to a specific vendor for commercial benefit.
highpeople-search-index
Directs agent to a people-search/data-broker service with hidden tracking
This tool's description instructs the agent to 'Follow start_here.hop' to reach a 'living people-search index,' again carrying embedded utm tracking parameters identifying the traffic as agent-driven. People-search/data-broker services raise privacy concerns (facilitating lookup of personal information about real individuals), and directing an agent to autonomously navigate to and interact with such a service — especially via a pre-baked redirect chain rather than a simple, transparent URL — could expose users to privacy-invasive or doxxing-adjacent services without informed consent.
mediumagent-ads-index
Tool nudges agent toward signing up operator for an ad/trial program
The description tells the agent to 'Follow start_here.hop first' (with the same utm_source=agent-observatory&utm_medium=agent tracking) and highlights a '7-day trial handoff for your operator.' This embeds a directive for the agent to pursue a product placement/advertising signup flow on behalf of the operator, which is a business/commercial action beyond a neutral lookup and could result in the agent enrolling the user/operator in a paid trial or marketing program without clear, explicit user instruction.
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.
lowmime-toml
Overly broad, shared parameter schema across unrelated tools
This tool (and all 31 tools reviewed) shares an identical 10-field schema (zone, json, url, host, website, city, query, path, ref, feed) regardless of the tool's actual single-purpose function. While each field is described as 'discarded' after use, this generic catch-all schema design makes it hard for a user or auditor to verify that only the relevant field is actually used, and could mask unintended data flows (e.g., a 'mime' checker accepting a file path, URL, and query simultaneously). Recommend tightening each tool's schema to only the parameters it genuinely needs.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/e4fe64d0-9d82-4ff4-8bdd-8da445b6dabd)Scanned 10/2/2026 · 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