S
sunglasses-dev/sunglasses
Open source input firewall for AI agents, beta.
★ 11·updated 2026-11-17
View on GitHub ↗Direct link · no redirect page
We have no copy-paste install command and no public remote endpoint, so we do not print a config. The step above is reference only, not a command we can vouch for. A made-up one is worse than none. How each client wires MCP up →
- Star count
- 11 ★ · sunglasses-dev/sunglasses · read from the GitHub search API · (checked 2026-11-19 20:00:48)
- Source
- collected from the punkpeye/awesome-mcp-servers list · type: MCP server
- Harvest history
- first seen 2026-11-18 · last seen 2026-11-20 · seen 3× · listed by 3 sources
- Score
- score 300 · 11 ★ · 3 sources · mcp
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: MCP servers. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
sunglasses-dev/sunglasses;first catalogued 2026-11-18;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.README excerpt (English, untranslated) · Read the full README on GitHub →
# SUNGLASSES
Excerpted from the repository README (abridged)
Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,494 patterns that carry a matcher (1,565 are listed) across 117 listed categories and reports findings and incomplete scans. When the scanner cannot read part of an input, it says so and exits 3; an incomplete scan is never reported as clean. 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
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
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.
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
bash
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
$ sunglasses scan --file vendor-brief.md # a vendor brief with an instruction buried in it
BLOCK [HIGH] — 6 threat(s) found:
1. [HIGH] Ignore previous instructions GLS-PI-001
… findings 2-5 omitted …
6. [HIGH] Data exfiltration to sink (mechanism) GLS-MECH-003
scanner exit code: 1
$ sunglasses scan --file attachments.zip # an archive we do not extract
INCOMPLETE
No findings in the inspected scope. Part of this input was not read, so this is
not a clean result.
scanner exit code: 3
$ sunglasses scan --file missing.md
What works today
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
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.
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
bash
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
$ sunglasses scan --file vendor-brief.md # a vendor brief with an instruction buried in it
BLOCK [HIGH] — 6 threat(s) found:
1. [HIGH] Ignore previous instructions GLS-PI-001
… findings 2-5 omitted …
6. [HIGH] Data exfiltration to sink (mechanism) GLS-MECH-003
scanner exit code: 1
$ sunglasses scan --file attachments.zip # an archive we do not extract
INCOMPLETE
No findings in the inspected scope. Part of this input was not read, so this is
not a clean result.
scanner exit code: 3
$ sunglasses scan --file missing.md
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/sunglasses-dev-sunglasses/)
- Source
- awesome · https://github.com/sunglasses-dev/sunglasses
- Browse by field
- MCP servers
- Traction
- 11 ★
- Listed by
- 3 independent sources
- added
- today
More MCP servers
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.