MCP.Market

SUNGLASSES MCP server

by sunglasses-dev·io.github.sunglasses-dev/sunglasses·v0.6.8·10 stars

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

C57/100grade C
What users say
No reviews yet
Be the first
Safety scan
C57/100

full report

Adoption
Growing

10 stars308 downloads/wk

Reviews

Write one

Nobody has reviewed SUNGLASSES yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

SUNGLASSES tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it

1 high2 medium
  • Code scan1500 source files scanned3/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (3)

  • mediumeval / new Function usedexec.eval
    sunglasses-0.6.8/attack-db/attacks/agent-workflow-security/GLS-AW-048-guardrail-evaluation-fixture-tampering.json: …rge|rewrite|weaken|poison|mutate)\\s+(?:eval(?:uation)?|test|guardrail|benchmark|redt…
  • highShell command built from a string (injection risk)exec.shell-concat
    sunglasses-0.6.8/attack-db/attacks/command-injection/GLS-CI-004-unquoted-shell-interpolation-injection.json: …", "subprocess without shlex", "os.system(f", "shell=True", "subprocess.call…
  • mediumsubprocess with shell=Trueexec.shell-true
    sunglasses-0.6.8/attack-db/attacks/command-injection/GLS-CI-004-unquoted-shell-interpolation-injection.json: …without shlex", "os.system(f", "shell=True", "subprocess.call(f", "subproc…
Overall 57/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How SUNGLASSES compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
57/100
higher than 14% of 4,460 AI and agents servers
GitHub stars
10
more than 84% of 2,711 AI and agents servers
Downloads a week
308
more than 80% of 1,538 AI and agents servers with a package

Install SUNGLASSES in Claude Code, Cursor or VS Code

claude mcp add sunglasses -- uvx sunglasses
Add to Cursor

What the publisher says

From the SUNGLASSES repository's README, as published. We do not edit it. Read it on GitHub

SUNGLASSES

<!-- mcp-name: io.github.sunglasses-dev/sunglasses -->

Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,569 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists, before a tool runs, best effort under its 10 second timeout.

What works today

approves the server at an interactive terminal. Once approved, it withholds a credential in a tool call or in a tool result, which is the credential lane and not general inspection of everything a tool returns. Installing it is not protection on its own. See What the proxy enforces.

  • Scan text, files, PDFs, images and QR codes from the CLI or from Python
  • An MCP server your agent calls, and a GitHub Action that scans every pull request
  • A Claude Code hook that blocks the credential paths and policy violations your policy lists, before a tool runs
  • A local MCP proxy that refuses every tools/list and tools/call until a person
  • Outside that lane this reads input, so a clean result is a confidence floor and not a guarantee

Sunglasses is a local, open-source scanner for text and supported files. It reports what it matched and what it could not read, so you can decide what to pass onward. It produces findings and an exit status; a CI job, a Claude Code hook or your own code acts on that result.

Sixty seconds

python3 -m venv .venv && source .venv/bin/activate
python -m pip install --upgrade sunglasses
curl -fsSL -o sixty-seconds.sh https://raw.githubusercontent.com/sunglasses-dev/sunglasses/main/demo/sixty-seconds.sh && bash sixty-seconds.sh

An activated virtualenv keeps the install and the sunglasses your shell resolves in the same environment, and --upgrade matters if you already have an older version. curl -fsSL fails on an HTTP error instead of saving the error page, so the script only runs if the download actually succeeded.

The script writes three fixture files into a temp directory, and deliberately scans a fourth path that does not exist, five scanner invocations in total, because the archive is scanned twice (human output and JSON). The script's own commands execute; scanned content stays data (it is never executed, and the ZIP is not extracted).

Abbreviated output, recorded on 0.5.6. Finding rows 2-5 are omitted below; timings and presentation are not shown because they vary:

$ sunglasses scan --file notes.md            # ordinary sprint notes
  PASS — No threats detected.
scanner exit code: 0

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

SUNGLASSES: common questions

Is SUNGLASSES MCP server safe?
With care: it is graded C, so read the findings first (57/100). Read the SUNGLASSES safety report
How do I install SUNGLASSES?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does SUNGLASSES need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is SUNGLASSES maintained?
The last commit was 21 days ago (2026-10-13). The latest release is v0.6.8.
What can I use instead of SUNGLASSES?
Servers from other publishers that do the same job: Basic Memory MCP server, PaperBanana MCP server and Decionis MCP server.
How does SUNGLASSES compare with other AI and agents MCP servers?
safety score 57/100 (higher than 14% of 4,460 AI and agents servers); github stars 10 (more than 84% of 2,711 AI and agents servers); downloads a week 308 (more than 80% of 1,538 AI and agents servers with a package). Full comparison.

Alternatives to SUNGLASSES

Same job from other publishers: the closest match first, then the best rated.

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • PaperBanana
    Generate academic diagrams and statistical plots from text using multi-agent AI.
    A
  • Decionis
    Authorize consequential AI agent actions before execution
    A
  • Godot MCP
    Agent-driven Godot playtesting: editor control, input injection, game-time stepping, live state.
    A
  • Openflowkit
    Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.
    A