Let Claude, ChatGPT, and other MCP clients capture, compare, and analyze any web page — hosted with OAuth, or local over stdio.
- capability exposure inferred + 24
- trust mitigators mixed − 11
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 7m ago · see ecosystem CVEs →
- B · 21 → A · 13
- B · 24 → B · 21
No known CVEs for this server.
- low dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (snapshot-site-snapshot-site-mcp-d1
- low dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (snapshot-site-snapshot-site-mcp-d1
- low dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (snapshot-site-snapshot-site-mcp-d1
[](https://mcpobservatory.com/servers/github:snapshot-site/snapshot-site-mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of snapshot-site.