Server definition

Hash: sha256:98852495cd03d29e46d66976399f90af41f92236847f208bca474ca9158d64c1
What it is: What a remote MCP server returned when asked what it offers: 3 tools

The blob, as servednamed by its sha256

{
  "instructions": "Hosted OpenCV for finding a pattern image inside a larger image: template matching, ORB/SIFT feature matching and RANSAC homography, over HTTP and MCP. Gives automation agents pixel boxes, corners and confidence for UI elements, logos and objects in screenshots. A hosted alternative to running OpenCV (opencv/opencv) yourself. Each tool is a paid call; set \"Authorization: Bearer <API key>\" (prepaid credits from https://pay.saastemly.com/credits/checkout).",
  "tools": [
    {
      "description": "Match local features between a pattern image and a larger image: detects ORB or SIFT keypoints in both, matches them with a brute-force matcher and Lowe's ratio test (OpenCV BFMatcher.knnMatch), and returns the good matches as point pairs sorted by distance. Use it to see which parts of a pattern are present and where, even when the pattern is scaled or rotated; for the pattern's outline use /v1/homography. Price: $0.004 a call (3 free calls a day without an API key).",
      "inputSchema": {
        "properties": {
          "detector": {
            "description": "Keypoint detector and descriptor: orb (default, fast, binary descriptors, Hamming distance) or sift (slower, better with scale changes, L2 distance)",
            "enum": [
              "orb",
              "sift"
            ],
            "type": "string"
          },
          "image": {
            "description": "Base64 of a PNG, JPEG, BMP or WebP file (a data: URI also works). At most 4 million pixels and about 2 MB. Alpha is dropped.",
            "type": "string"
          },
          "max_features": {
            "description": "Most keypoints kept per image, 100-5000 (default 2000)",
            "type": "integer"
          },
          "max_matches": {
            "description": "Most matches listed, 1-200 (default 50); goodMatches always counts all of them",
            "type": "integer"
          },
          "ratio": {
            "description": "Lowe's ratio test threshold, 0.5-0.95 (default 0.75): a match is kept when its distance is below ratio times the second-best distance",
            "type": "number"
          },
          "template": {
            "description": "Base64 of the pattern to find, same formats. At most 1 million pixels and about 1 MB.",
            "type": "string"
          }
        },
        "required": [
          "image",
          "template"
        ],
        "type": "object"
      },
      "name": "feature-match",
      "outputSchema": null
    },
    {
      "description": "Locate a pattern image inside a larger image even when it is scaled, rotated or viewed at an angle: ORB or SIFT feature matching plus cv2.findHomography with RANSAC. Returns whether it was found, the 3x3 homography (pattern pixels to image pixels), the four projected corners, the bounding box, and the inlier count as confidence. Use it to find a UI element, logo or object in a screenshot or photo. Price: $0.004 a call (3 free calls a day without an API key).",
      "inputSchema": {
        "properties": {
          "detector": {
            "description": "Keypoint detector and descriptor: orb (default, fast, binary descriptors, Hamming distance) or sift (slower, better with scale changes, L2 distance)",
            "enum": [
              "orb",
              "sift"
            ],
            "type": "string"
          },
          "image": {
            "description": "Base64 of a PNG, JPEG, BMP or WebP file (a data: URI also works). At most 4 million pixels and about 2 MB. Alpha is dropped.",
            "type": "string"
          },
          "max_features": {
            "description": "Most keypoints kept per image, 100-5000 (default 2000)",
            "type": "integer"
          },
          "min_inliers": {
            "description": "Fewest RANSAC inliers for found to be true, 4-200 (default 10)",
            "type": "integer"
          },
          "ratio": {
            "description": "Lowe's ratio test threshold, 0.5-0.95 (default 0.75): a match is kept when its distance is below ratio times the second-best distance",
            "type": "number"
          },
          "reproj_threshold": {
            "description": "RANSAC reprojection error in pixels below which a match is an inlier, 0.5-20 (default 3)",
            "type": "number"
          },
          "template": {
            "description": "Base64 of the pattern to find, same formats. At most 1 million pixels and about 1 MB. Needs visible texture or corners; a flat-coloured pattern has no features.",
            "type": "string"
          }
        },
        "required": [
          "image",
          "template"
        ],
        "type": "object"
      },
      "name": "homography",
      "outputSchema": null
    },
    {
      "description": "Find where a small pattern image (a button, icon, logo or crop) appears inside a larger screenshot or picture, using OpenCV cv2.matchTemplate. Returns the best position, plus every non-overlapping position scoring above the threshold, as pixel boxes with scores. Use it for exact-looking pixel patterns at the same scale; for different scale, rotation or perspective use /v1/homography. Price: $0.003 a call (3 free calls a day without an API key).",
      "inputSchema": {
        "properties": {
          "grayscale": {
            "description": "Match on grayscale versions of both images (default false: match all three colour channels)",
            "type": "boolean"
          },
          "image": {
            "description": "Base64 of a PNG, JPEG, BMP or WebP file (a data: URI also works). At most 4 million pixels and about 2 MB. Alpha is dropped.",
            "type": "string"
          },
          "max_matches": {
            "description": "Most matches returned, 1-50 (default 5); overlapping positions are suppressed",
            "type": "integer"
          },
          "method": {
            "description": "OpenCV matching method (default TM_CCOEFF_NORMED, robust to brightness change). Scores are 0-1, higher is better; for TM_SQDIFF_NORMED the score is 1 minus the squared-difference value",
            "enum": [
              "TM_CCOEFF_NORMED",
              "TM_CCORR_NORMED",
              "TM_SQDIFF_NORMED"
            ],
            "type": "string"
          },
          "template": {
            "description": "Base64 of the pattern to find, same formats. At most 1 million pixels and about 1 MB. Must fit inside the image.",
            "type": "string"
          },
          "threshold": {
            "description": "Minimum score for a match, 0-1 (default 0.8)",
            "type": "number"
          }
        },
        "required": [
          "image",
          "template"
        ],
        "type": "object"
      },
      "name": "template-match",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:98852495cd03d29e46d66976399f90af41f92236847f208bca474ca9158d64c1 | sha256sum