ModelsAtlas
Explore
Atlas / MCP servers / mario-andreschak / Image Recognition

Image RecognitionSAFE

mcp/mario-andreschak/image-recognition
MCP server by mario-andreschak · Audited 2026-10-08
⚑ Report / re-scanSource ↗

An MCP server that provides image recognition 👀 capabilities using Anthropic and OpenAI vision APIs

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
2 2r · 0w · 0d
Transport
—
License
MIT
Stars
40
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

An MCP server that provides image recognition capabilities using Anthropic and OpenAI vision APIs. Version 0.1.2.

Features

  • Image description using Anthropic Claude Vision or OpenAI GPT-4 Vision
  • Support for multiple image formats (JPEG, PNG, GIF, WebP)
  • Configurable primary and fallback providers
  • Base64 and file-based image input support
  • Optional text extraction using Tesseract OCR

Requirements

  • Python 3.8 or higher
  • Tesseract OCR (optional) - Required for text extraction feature
  • Windows: Download and install from UB-Mannheim/tesseract
  • Linux: sudo apt-get install tesseract-ocr
  • macOS: brew install tesseract

Installation

  1. Clone the repository:
git clone https://github.com/mario-andreschak/mcp-image-recognition.git
cd mcp-image-recognition
  1. Create and configure your environment file:
cp .env.example .env
# Edit .env with your API keys and preferences
  1. Build the project:
build.bat

Usage

Running the Server

Spawn the server using python:

python -m image_recognition_server.server

Start the server using batch instead:

run.bat server

Start the server in development mode with the MCP Inspector:

run.bat debug

Available Tools

  1. describe_image
  2. Input: Base64-encoded image data and MIME type
  3. Output: Detailed description of the image
  1. describe_image_from_file
  2. Input: Path to an image file
  3. Output: Detailed description of the image

Environment Configuration

  • ANTHROPIC_API_KEY: Your Anthropic API key.
  • OPENAI_API_KEY: Your OpenAI API key.
  • VISION_PROVIDER: Primary vision provider (anthropic or openai).
  • FALLBACK_PROVIDER: Optional fallback provider.
  • LOG_LEVEL: Logging level (DEBUG, INFO, WARNING, ERROR).
  • ENABLE_OCR: Enable Tesseract OCR text extraction (true or false).
  • TESSERACT_CMD: Optional custom path t
Read from source at commit b500395bfa8bOBSERVED · 2026-10-08
02

Exposed tools (2)

2 read · 0 write · 0 destructive.

ToolRiskDescription
describe_imagereadDescribe the contents of an image using vision AI.
describe_image_from_filereadDescribe the contents of an image file using vision AI.
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (6)

LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
src/image_recognition_server/server.py:108
image_bytes = base64.b64decode(image_data)
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
src/image_recognition_server/utils/image.py:74
image_data = base64.b64decode(base64_string)
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
tests/test_server.py:12
bytes.fromhex(
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
tests/test_server.py:66
image_data = base64.b64decode(TEST_IMAGE_DATA)
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements-dev.txt
pytest, pytest-asyncio, pytest-cov, black, isort, mypy, ruff
Why it matters. 7 requirement(s) not pinned with ==
Fix. pin exact versions
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements.txt
mcp, anthropic, openai, python-dotenv, Pillow, numpy, pandas, pytesseract
Why it matters. 8 requirement(s) not pinned with ==
Fix. pin exact versions

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha b500395bfa8bfull audit observations/trust-audit/mcp-server/mario-andreschak__image-recognition.json · Report an issue / request a re-scan
04

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08b500395bfa8bSAFEB89first audit
05

Questions

What is the Image Recognition MCP server?

An MCP server that provides image recognition 👀 capabilities using Anthropic and OpenAI vision APIs

What tools does Image Recognition expose?

2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Image Recognition safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Image Recognition need?

It reads ANTHROPIC_API_KEY and OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How current is this page?

The grade is for one exact copy of the source (b500395bfa8b), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement