Skip to main content
Glama

agent-vision-mcp (hardened)

A hardened fork of @kitlau/agent-vision-mcp — an MCP server that gives non-vision LLMs the ability to analyze images via any OpenAI-compatible vision API (Claude Code, DeepSeek, etc.).

This build fixes intermittent empty / truncated image-analysis results and request hangs that affect long outputs (e.g. high-resolution 3D render screenshots) against self-hosted Qwen VLMs and similar backends.

What was broken upstream

The upstream package:

  • defaulted output max_tokens to 1024 and never grew it, so long analyses hit finish_reason: length and were cut off mid-sentence — and intermittently returned empty content, surfacing as ❌ 视觉 API 返回的内容为空;

  • only read message.content, ignoring message.reasoning_content used by Qwen3.x thinking-style models;

  • had no retry on empty / 5xx / 429 / transient network errors;

  • set no client timeout, so slow high-res inference could hang and get killed (MCP error -32001: user-cancel).

Related MCP server: image_mcp

What this build changes

dist/vision-client.js:

  • Grows max_tokens on truncation (finish_reason === "length") and retries, so a low ceiling can never silently produce a partial/empty answer (grow ceiling: 32768).

  • Falls back to message.reasoning_content when content is empty (Qwen thinking mode).

  • Retries on empty results, 5xx, 429, and network/timeout errors with exponential backoff (default 3 retries).

  • Sets an explicit client timeout (default 300000 ms) to prevent hangs.

dist/config.js:

  • Adds VISION_MAX_TOKENS (default 16384), VISION_TIMEOUT_MS (default 300000), VISION_MAX_RETRIES (default 3) env vars, exposed on the config object.

Install as an MCP server

Point your MCP client at this repo. Example claude_desktop_config.json / .mcp.json / global ~/.claude.json entry:

{
  "mcpServers": {
    "agent-vision": {
      "type": "stdio",
      "command": "node",
      "args": ["path/to/this/repo/dist/index.js"]
    }
  }
}

For a drop-in remote install, clone this repo and npm install, then run node dist/index.js. Or add it as a dependency with npm install github:aabbccddwasd/agent-vision-mcp.

Environment variables

Variable

Default

Description

VISION_API_KEY

(required)

API key for the OpenAI-compatible endpoint

VISION_BASE_URL

https://api.openai.com/v1

OpenAI-compatible base URL

VISION_MODEL_NAME

gpt-4o

The vision model, e.g. Qwen3.6-35B-A3B

VISION_MAX_TOKENS

16384

Output token budget (was 1024 upstream)

VISION_TIMEOUT_MS

300000

Per-request client timeout

VISION_MAX_RETRIES

3

Retries for empty / 5xx / 429 / network errors

VISION_CACHE_ENABLED

false

Optional disk response cache

VISION_CACHE_DIR

<tmp>/agent-vision-cache

Cache directory (when enabled)

VISION_MAX_IMAGE_SIZE

20971520

Max image bytes (20 MB)

License

MIT. Original author: kitlau86.

Available Tools

1 tool
analyze_imageAnalyze ImageA
Read-onlyIdempotent

Analyze an image with a vision AI model, giving a non-vision main model the ability to "see" image content. Call this when the user sends an image, or when you need to understand an image (describe it, OCR text, identify UI elements, read charts, etc.). The image can be provided as a base64 data URL, an HTTP(S) link, or a local file path.

Inputs: image (required), prompt (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.5/5.0

    Scored across 1 tool

    Disambiguation5/5

    There is only one tool, so there is no possibility of ambiguity or misselection. The tool's purpose is clearly distinct and singular.

    Naming Consistency5/5

    With a single tool named 'analyze_image', the naming follows a clear and consistent verb_noun pattern. There are no other tools to introduce inconsistency.

    Tool Count4/5

    The server has only one tool, which is below the typical 3-15 range, but it is a narrow-purpose server focused on image analysis. The single tool is well-scoped and earns its place, making the count slightly under but reasonable.

    Completeness5/5

    The single tool covers a wide range of image analysis needs—description, OCR, UI element detection, chart reading, etc. There are no obvious gaps for the stated purpose of giving a non-vision model the ability to see.

    Related MCP Connectors

    Related MCP Servers