Security / SUNGLASSES

SUNGLASSES

io.github.sunglasses-dev/sunglasses · v0.6.8

Input firewall for AI agents: scan text and files before an agent reads them. Local, no network.

Description supplied by the publisher in the MCP Registry. We have not tested this server.

GitHub repositoryWebsiteCompare alternatives

Install

uvx -m sunglasses.mcp sunglasses

Assembled from the package metadata in the official MCP Registry (including any subcommand or flag the publisher lists). Some publishers do not list the subcommand that starts MCP mode, so confirm the command in the README, along with any required configuration and credentials, before connecting it to real data.

Signals

GitHub stars10
npm weekly downloads-
Last push3d ago
LicenceMIT
Open issues4
SECURITY.mdYes
LanguagePython
Latest version published2026-10-13

Signals captured from GitHub, npm and the official MCP Registry on October 15, 2026. See the scoring method.

Similar servers compare all →

agent-firewall-mcp

Score 71

Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.

★ 1↓ 72/wkMITpushed 2d ago
Security

NetsCLI

Score 85

Network scanner for AI agents: discover hosts, scan TCP and UDP ports, query DNS and mDNS.

★ 16↓ 38/wkMITpushed 4d ago
Security

Koma Gate MCP

Score 84

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

★ 13↓ 27/wkMITpushed 4d ago
Security