Skip to main content
Glama
avdivo

opencode-vision-mcp

by avdivo
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

opencode-vision-mcp

MCP-сервер для распознавания изображений. Отправляет картинку в OpenRouter AI и возвращает текстовое описание.

Использует две модели для надёжности: быструю (primary) и запасную (fallback).

Быстрая установка

Linux / macOS:

curl -sL https://github.com/avdivo/opencode-vision-mcp/raw/main/install.sh | bash

Windows (PowerShell):

iwr https://github.com/avdivo/opencode-vision-mcp/raw/main/install.ps1 | iex

Скрипты установят uv (если нет), скачают пакет из GitHub и установят команду opencode-vision-mcp в систему. После установки ключ нужно будет указать в конфиге.

Related MCP server: image-mcp

Ручная установка

1. Установите uv

curl -LsSf https://astral.sh/uv/install.sh | sh

2. Установите пакет

uv tool install --from git+https://github.com/avdivo/opencode-vision-mcp opencode-vision-mcp

3. Добавьте в opencode.jsonc

{
  "mcp": {
    "vision": {
      "command": "opencode-vision-mcp",
      "args": [],
      "env": {
        "OPENROUTER_API_KEY": "sk-or-v1-..."
      },
      "timeout": 120000
    }
  }
}

Настройка (опционально)

Модели можно переопределить через переменные окружения:

Переменная

По умолчанию

Описание

OPENROUTER_API_KEY

—

Обязательно. Ключ API OpenRouter

VISION_MODEL

google/gemma-4-31b-it

Основная модель

VISION_FALLBACK_MODEL

qwen/qwen3-vl-32b-instruct

Запасная модель

OPENROUTER_API_KEY="sk-or-v1-..." \
  VISION_MODEL="google/gemma-4-31b-it" \
  VISION_FALLBACK_MODEL="qwen/qwen3-vl-32b-instruct" \
  uvx --from git+https://github.com/avdivo/opencode-vision-mcp opencode-vision-mcp

Как это работает

Сервер читает stdin/stdout по протоколу JSON-RPC (MCP).

Инструмент: read_image(file_path, prompt?)

  • file_path — путь к изображению

  • prompt — вопрос по картинке (по умолчанию "Опиши, что изображено на картинке")

Сервер:

  1. Кодирует изображение в base64

  2. Отправляет в OpenRouter (primary модель)

  3. Если primary не ответила за 30 секунд — шлёт fallback модели

  4. Возвращает текстовый ответ

Цена

  • Primary модель: ~$0.0002 за скриншот

  • Fallback модель: ~$0.0004 за скриншот

  • primary срабатывает в большинстве случаев

Available Tools

1 tool
read_imageA

Анализирует изображение: распознаёт текст, объекты, сцены. Принимает путь к файлу и опциональный вопрос.

ParametersJSON Schema
NameRequiredDescriptionDefault
promptNoВопрос или инструкция по картинке (по умолчанию: 'Опиши, что изображено на картинке')
file_pathYesАбсолютный путь к файлу изображения (.jpg, .png, .webp, .bmp)

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are provided, so the description must cover behavioral traits. It mentions the tool analyzes images and recognizes text/objects/scenes, implying it is a read operation, but does not disclose error behavior, permissions, or output format. The description is adequate but not comprehensive.

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

Conciseness4/5

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

The description is two short sentences in Russian, conveying the core purpose efficiently without fluff. It is concise and front-loaded with the main action.

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

Completeness3/5

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

With no output schema and simple parameters, the description covers the tool's function moderately well. However, it does not describe the return value or handling of errors, leaving some gaps for an AI agent to infer.

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%, so the description adds minimal value beyond the schema. It reiterates that the tool takes a file path and optional question, but does not mention the default prompt value already in the schema. Baseline score of 3 is appropriate.

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 clearly states the tool analyzes images and recognizes text, objects, and scenes. It specifies inputs (file path and optional question), making the purpose explicit and unambiguous.

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

Usage Guidelines3/5

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

The description implies usage by mentioning inputs (file path and question) but provides no guidance on when to use this tool versus alternatives or any exclusions. Since no sibling tools exist, the lack of differentiation is acceptable, but explicit usage context is missing.

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 updatev1.0.0
    • First observedread_image
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

With only one tool, there is no ambiguity between tools. The purpose is clear and distinct.

Naming Consistency5/5

A single tool name follows a clear verb_noun pattern (read_image) and there is no inconsistency.

Tool Count3/5

The server has a single tool, which feels thin for a vision-oriented server. While it can handle multiple tasks within one tool, the scope suggests more tools would be expected for a complete set.

Completeness3/5

The single tool covers text, object, and scene recognition with optional questions, but lacks other common operations like listing images, generating descriptions, or handling multiple images in batch. There are moderate gaps for typical vision use cases.

Maintenance

ActivitySlowing
ResponsivenessSyncing

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/avdivo/opencode-vision-mcp'

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