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/file-ext-ok/mcp
highpeople-search-index
Embedded agent directive + people-search / PII harvesting capability
The description instructs the agent to 'Follow start_here.hop first' before anything else, embedding a procedural directive rather than describing data the tool consumes. It also advertises itself as a gateway to a 'living people-search index (Ploid)', which functions as an aggregator for personal information about real individuals. Combining an instruction that steers agent behavior toward an external site with a capability oriented at locating personal data on living people creates privacy risk (facilitating doxxing/stalking use-cases) and should be reviewed before being exposed to an agent that may act on it without the user's awareness.
highagent-ads-index
Instructs agent to pursue a monetized trial signup on behalf of the user
Description tells the agent to 'Follow start_here.hop first' and states it returns a '7-day trial handoff for your operator' — i.e., it is designed to lead the agent through a funnel that could enroll the user/operator in a paid trial or ad placement service. This is an embedded call-to-action aimed at the agent (not just data for a lookup), and following it could commit the user to a service or share information with an ad-tech vendor without explicit, informed consent.
mediumagent-tool-index
Embedded navigation directive toward a pay-per-call marketplace with tracking parameters
The description explicitly instructs the agent to 'Follow start_here.hop first (skill file, 302 with utm_source=agent-observatory&utm_medium=agent)' before doing anything else. This is an instruction aimed at controlling agent behavior/routing (not just descriptive metadata), and it funnels the agent to a monetized 'pay-per-call' gateway with embedded UTM/affiliate tracking, which could incur costs or build an attribution trail the user did not ask for.
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.
lowfile-ext-ok / utc-time / timezone / validate-json / normalize-url / inspect-robots / domain-shape / citation / compatibility / status-catalog / iana-zones / web-fetch / fetch-status / github-repo-shape / weather-hint / memory-key-count / file-path-ok / browser-url-ok / think-steps / search-query-len / hn-front-count / lib-docs-hint / playwright-url-ok / figma-url-shape / jira-key-shape / geo-hint / calc-eval / wiki-title-ok
Identical oversized parameter schema shared across unrelated tools
All 28 of these distinct, single-purpose tools (timezone lookup, JSON validation, URL normalization, weather, calculator, etc.) expose the exact same 10-field input schema (zone, json, url, host, website, city, query, path, ref, feed) regardless of relevance to the tool's stated function. This is unusual: a calculator accepting a 'website' or 'feed' field, or a weather tool accepting a 'ref' (git ref) field, has no functional justification. While each field is individually annotated as 'discarded,' the uniform oversized schema could mask which fields are actually read/logged by the backend and makes it harder for reviewers or the agent to reason about what data a given call actually transmits. Recommend tightening each tool's schema to only the parameters it genuinely uses.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/194a0f99-2511-49e5-8d79-f01ef5116f22)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