Skip to main content
Glama
aabbccddwasd

agent-vision-mcp

by aabbccddwasd
OverviewSchemaRelated ServersScoreDiscussions
Remote

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
imageYesThe image to analyze. Accepts a base64 data URL (data:image/...), an HTTP/HTTPS link, or a local file path. Formats: JPEG, PNG, WebP, GIF, BMP.
promptYesWhat you want analyzed or extracted from the image, e.g. 'Describe this image in detail' or 'Extract all visible text (OCR)'.

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds that it uses a vision AI model and details supported input formats (base64 data URL, HTTP link, local file path). It doesn't disclose failure modes or rate limits, but given the annotation coverage, this is a meaningful addition.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three succinct sentences: purpose, when to call, and input formats. It is front-loaded with the primary function and every sentence contributes distinct value without redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only analysis tool with two well-documented parameters, the description covers the purpose, usage, and input formats thoroughly. The 'see' metaphor implies a textual output, and the examples clarify what to expect. It omits explicit return format or size limits, but those are not critical for an AI agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both 'image' and 'prompt' clearly documented including formats, requirements, and examples. The description adds no new parameter-level information beyond what the schema provides, so it does not exceed the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Analyze' with the resource 'image', immediately clarifying the tool's function. It goes further by explaining the purpose ('giving a non-vision main model the ability to see') and listing concrete use cases (describe, OCR, identify UI elements, read charts). There are no siblings, so differentiation is not required.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states 'Call this when the user sends an image, or when you need to understand an image', providing clear trigger conditions. It also enumerates example analysis types, which helps the agent decide when to use the tool. No alternatives exist, but the guidance is strong and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev0.2.0-hardened
    • First observedanalyze_image
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.5/5.0
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.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aabbccddwasd/agent-vision-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server