1. Conduid
  2. Browser
  3. My Own Vision MCP
MCP server · Browser

My Own Vision MCP

by · github.com/vectorequa/my-own-vision-mcp

Standalone MCP server for image recognition via LLM vision API — OCR, image analysis, structured extraction, screenshot-to-accessibility-tree

Unclaimed accessibilityai-agentcomputer-visionimage-analysisllmmcpmodel-context-protocolocropenai-compatiblescreenshotvision
InstallView source
34Low

Scored a month ago · breakdown

About My Own Vision MCP

My Own Vision MCP is an MCP server published by vectorequa in the Browser category: standalone MCP server for image recognition via LLM vision API — OCR, image analysis, structured extraction, screenshot-to-accessibility-tree.

Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/vectorequa/my-own-vision-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about My Own Vision MCP

Powered by Claude · Grounded in docs

I know everything about My Own Vision MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v2026.09.5v2026.09.5 (0.1.6) · 18 Sep 2026min_image_dim support + 4K resolution for qwen3.6-35b min_image_dim — per-provider minimum image dimension Add `min_image_dim` to `ProviderCapabilities` and `VisionConfig`. Images smaller than the minimum are automatically upscaled using…
v2026.09.4v2026.09.4 (0.1.5) · 18 Sep 2026extra_body — per-provider vendor-specific parameter passthrough Add `extra_body` to any provider config to pass vendor-specific fields directly into the LLM request body. Standard fields (model, messages, max_tokens) always override.…
v2026.09.3v2026.09.3 (0.1.4) · 18 Sep 2026Changes feat: extract_text custom prompt + simplified OCR default (494cc45) `extract_text`: add optional `prompt` param for custom OCR instructions Simplify `DEFAULT_OCR_PROMPT` (auto-detect instead of hardcoded language list) feat: SSRF…
v2026.09.0v2026.09.0 (SemVer 0.1.1) · 16 Sep 2026Initial release after orphan reset. Features 6 MCP tools**: analyze_image, extract_text, extract_structured, compare_images, analyze_screenshot, ping 4 MCP prompts**: ocr, describe, compare, ui-tree Any OpenAI-compatible vision API…
Questions

About My Own Vision MCP

How do I install My Own Vision MCP?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is My Own Vision MCP safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is My Own Vision MCP still maintained?

Yes — the latest release is v2026.09.5 (18 Sep 2026), and the last commit was 29 days ago. The repository has 0 stars.