// SCAN REPORT

farshid-mcp-imageProcessing

47 tools. 26 can modify or destroy data without limits.

26 write tools that can modify data. Rate limits recommended.

Last updated:

26 can modify or destroy data
21 read-only
47 tools total

Community server · catalogue entry verified 30/06/2026

How to control farshid-mcp-imageProcessing ↓

TOOL MAP

What farshid-mcp-imageProcessing exposes to your agents

Read (21) Write / Execute (26) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
High Risk

The most dangerous farshid-mcp-imageProcessing tools

Execute · Low edges_canny This tool executes the Canny edge detection algorithm on an image, which is a computational operation/transform. Execute · High webcam_capture Accessing the webcam is an external operation that captures real-world imagery without user interaction per invocation. Execute · Medium webcam_preview This tool triggers an external operation — opening a GUI/preview window using OpenCV — which has side effects on the local system (UI rendering, window management, potential camera access). Execute · High webcam_record This tool activates the webcam hardware and records video, which is an external operation with privacy implications.

26 of farshid-mcp-imageProcessing's 47 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control farshid-mcp-imageProcessing

PolicyLayer is an MCP gateway — it sits between your AI agents and farshid-mcp-imageProcessing, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations
{
  "adjust_brightness_contrast": {
    "limits": [
      {
        "counter": "adjust_brightness_contrast_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "blur_median": {
    "limits": [
      {
        "counter": "blur_median_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register farshid-mcp-imageProcessing — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON FARSHID-MCP-IMAGEPROCESSING →

Instant setup, no code required.

FULL CATALOGUE

All 47 farshid-mcp-imageProcessing tools

EXECUTE 4 tools
Execute edges_canny Canny edge detector. Execute webcam_capture Capture one frame from the webcam and return it as a PNG image. Execute webcam_preview Open a local OpenCV preview window for up to N seconds (max 120). Execute webcam_record Record a short MP4 from the webcam for N seconds (max 120).
WRITE 22 tools
Write adjust_brightness_contrast Adjust brightness (-255..255) and contrast (multiplier, e.g. 1.2). Write blur_bilateral Edge-preserving bilateral filter. Write blur_gaussian Apply Gaussian blur. ksize is forced to odd. Write color_convert Convert color space. target: gray, hsv, hls, lab, ycrcb, rgb, bgr. Write denoise Non-local means denoising for color images. Write draw_circle Draw a circle. thickness=-1 fills. Write draw_line Draw a line. Write draw_rectangle Draw a rectangle on an image. Write draw_text Draw text on an image. Write histogram_equalize Equalize histogram. method: 'global' (single-channel only) or Write image_blend Blend two same-size images: out = aimg1 + (1-a)img2. Write image_concat Concatenate images horizontally or vertically (resized to common dim). Write image_convert Convert an image between formats by extension (e.g. .jpg, .png, .webp, .bmp). Write image_flip Flip image: horizontal (mirror), vertical, or both. Write image_pad Add borders/padding around an image. Write image_resize Resize an image. Provide either (width, height), or scale, or one of Write image_rotate Rotate an image by angle degrees (CCW). If keep_size is False the Write sharpen Unsharp-mask sharpening. amount ~ 0.5–2.0. Write threshold Binary threshold. method: binary, binary_inv, otsu, adaptive_mean, adaptive_gaussian. Write video_extract_frames Sample frames from a video and save them. Returns saved paths. Write video_thumbnail Save a single frame from a video at a given time as a thumbnail. Write webcam_save Capture a webcam frame and save to disk. If output_path is empty,
READ 21 tools
Read blur_median Median blur — good for salt-and-pepper noise. Read detect_bodies Detect full bodies with the bundled Haar cascade (low recall, demo only). Read detect_circles Hough circle detection. Read detect_corners Shi-Tomasi good-features-to-track corner detection. Read detect_eyes Detect eyes with the bundled Haar cascade. Read detect_faces Detect faces with the bundled Haar cascade. Returns bounding boxes. Read detect_lines Probabilistic Hough line detection. Read detect_qrcode Detect and decode QR codes. Read edges_laplacian Laplacian of an image. Read edges_sobel Sobel gradient magnitude. Read feature_match Detect and match ORB features between two images. Optionally save a Read find_contours Find contours after thresholding. Optionally draw them onto output_path. Read histogram_data Return per-channel histograms as lists (B, G, R or single 'gray'). Read image_crop Crop a rectangular region (x, y, width, height) from an image. Read image_diff Absolute difference between two images. Returns mean/max diff. Read image_info Return shape, dtype, channel count, file size, and basic stats. Read image_show Load an image from disk and return it as PNG to the chat. Read image_to_grayscale Convert image to single-channel grayscale. Read morphology Morphological op: erode, dilate, open, close, gradient, tophat, blackhat. Read template_match Find a template inside an image (TM_CCOEFF_NORMED). Returns matches above threshold. Read video_info Return video metadata (fps, width, height, frame count, duration).
FAQ

Questions about farshid-mcp-imageProcessing

How do I prevent bulk modifications through farshid-mcp-imageProcessing? +

The farshid-mcp-imageProcessing server has 22 write tools including adjust_brightness_contrast, blur_bilateral, blur_gaussian. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach farshid-mcp-imageProcessing.

How many tools does the farshid-mcp-imageProcessing MCP server expose? +

47 tools across 2 categories: Read, Write. 21 are read-only. 26 can modify, create, or delete data.

How do I enforce a policy on farshid-mcp-imageProcessing? +

Register the farshid-mcp-imageProcessing MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every farshid-mcp-imageProcessing tool call.

Deterministic rules across all 47 farshid-mcp-imageProcessing tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FARSHID-MCP-IMAGEPROCESSING →

Instant setup, no code required.

47 farshid-mcp-imageProcessing tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.