mcp-local-vision

jshsakura/mcp-local-vision

★ 0 stars JavaScript AI/LLM Updated today

Give text-only LLMs (GLM, DeepSeek, ...) eyes. MCP server that reads images and PDFs with a vision model on your own GPU — no API keys, nothing leaves the machine.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-local-vision": {
      "command": "npx",
      "args": [
        "-y",
        "jshsakura/mcp-local-vision"
      ]
    }
  }
}

README Excerpt

Lets a **text-only LLM read images and PDFs** by delegating to a vision model running on your own GPU, through `llama.cpp`. Built for the case where your coding model has no vision at all — GLM on the Z.AI coding plan, DeepSeek, most local models. The coding model stays where it is; this server becomes its eyes.

Tools (20)

VISION_ALLOWED_ROOTSVISION_API_KEYVISION_CONTEXTVISION_EXTRA_ARGSVISION_GPU_LAYERSVISION_HTTP_HOSTVISION_HTTP_PORTVISION_HTTP_TOKENVISION_IDLE_MSVISION_MANAGEDVISION_MAX_EDGEVISION_MAX_FILE_BYTESVISION_MAX_PAGESVISION_MAX_TOKENSVISION_MMPROJ_PATHVISION_MODEL_PATHVISION_NODEVISION_PDF_DPIVISION_SERVER_BINVISION_SERVER_URL

Topics

glmlocal-llmmcpmcp-serverocrollamaopencodepdfqwen3-vlvision

mcp-local-vision

Quick Install

README Excerpt

Tools (20)

Topics

Related AI/LLM Servers