Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "visionflow-match": {
      "type": "http",
      "url": "https://visionflow-match.saastemly.com/mcp",
      "headers": {
        "Authorization": "Bearer ${VISIONFLOW_MATCH_TOKEN}"
      }
    }
  }
}

claude mcp add --transport http visionflow-match https://visionflow-match.saastemly.com/mcp --header "Authorization: Bearer ${VISIONFLOW_MATCH_TOKEN}"

[mcp_servers.visionflow-match]
url = "https://visionflow-match.saastemly.com/mcp"
bearer_token_env_var = "VISIONFLOW_MATCH_TOKEN"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "visionflow-match": {
      "type": "remote",
      "url": "https://visionflow-match.saastemly.com/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:VISIONFLOW_MATCH_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "visionflow-match": {
      "type": "http",
      "url": "https://visionflow-match.saastemly.com/mcp",
      "headers": {
        "Authorization": "Bearer ${VISIONFLOW_MATCH_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=visionflow-match&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdmlzaW9uZmxvdy1tYXRjaC5zYWFzdGVtbHkuY29tL21jcCIsImhlYWRlcnMiOnsiQXV0aG9yaXphdGlvbiI6IkJlYXJlciAke1ZJU0lPTkZMT1dfTUFUQ0hfVE9LRU59In19"
}

{
  "servers": {
    "visionflow-match": {
      "type": "http",
      "url": "https://visionflow-match.saastemly.com/mcp",
      "headers": {
        "Authorization": "Bearer ${VISIONFLOW_MATCH_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "visionflow-match": {
      "httpUrl": "https://visionflow-match.saastemly.com/mcp",
      "headers": {
        "Authorization": "Bearer ${VISIONFLOW_MATCH_TOKEN}"
      }
    }
  }
}

extensions:
  "visionflow-match":
    enabled: true
    name: "visionflow-match"
    type: streamable_http
    uri: "https://visionflow-match.saastemly.com/mcp"
    headers:
      "Authorization": "Bearer ${VISIONFLOW_MATCH_TOKEN}"
    timeout: 300

Placeholders to fill from your own secret store: ${VISIONFLOW_MATCH_TOKEN}. The registry never accepts secret values.

Quality 79 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: template-match (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); feature-match (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); homography (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
pass
tools.token_costabout 1,162 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changes3 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

3 tools, about 1,162 tokens to load them all · tool set c1bf7b396ba9 · tools last changed 2026-10-04 · checked 2026-10-20 10:03 UTC

Tool changes

2026-10-04homographychangeddescription
before
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.
after · 89% of words in common
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).
2026-10-04feature-matchchangeddescription
before
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.
after · 88% of words in common
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).
2026-10-04template-matchchangeddescription
before
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.
after · 87% of words in common
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).

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 58 / 100

no-repository

provenance55

liveness18

freshness100

hygiene80

+dns-namespace +website -unreachable(2 failures) +updated-17d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://visionflow-match.saastemly.com/mcp` streamable-http	none	no (2 failures)	95%	227 ms	2025-06-18	2026-10-19

Tools (3)

`feature-match`	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).
`homography`	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).
`template-match`	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).

Schemas: list_tools.

Similar MCP servers

More from com.saastemly

And 1 more from this publisher.

Official server.json

{
  "name": "com.saastemly/visionflow-match",
  "icons": [
    {
      "src": "https://visionflow-match.saastemly.com/icon.svg",
      "mimeType": "image/svg+xml"
    }
  ],
  "title": "VisionFlow Match",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://visionflow-match.saastemly.com/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "description": "Bearer <API key>: prepaid credits from https://visionflow-match.saastemly.com (tools with a free tier work without one)"
        }
      ]
    }
  ],
  "version": "1.0.1791044159",
  "websiteUrl": "https://visionflow-match.saastemly.com",
  "description": "Hosted OpenCV for finding a pattern image inside a larger image: template matching, ORB/SIFT..."
}