Skip to main content
Glama

vision-mcp

Give a non-vision coding agent (OpenCode, Claude Code, Cursor, Cline, …) the ability to "see" an image — for UI/design review, OCR, "what's on this screenshot", or comparing a render to an expectation — using free OpenRouter vision models.

Zero dependencies. Speaks MCP over stdio. The agent calls one tool:

analyze_image(prompt, image)  ->  { content, servedModel, attempts, tried }
  • image = local file path or http(s) URL.

  • The server converts everything to base64 (the free nemotron endpoint rejects http image URLs but accepts base64), then calls OpenRouter.

  • Model chain: several free vision models first (each with retries), then a cheap paid fallback. First model that answers wins; the result says which one served it.

Why

Agents without native vision cannot judge whether a game/UI looks good. Numeric layout checks catch clipping, not beauty. This tool lets the agent itself run a design review on Playwright screenshots before shipping — no need to pick a vision subagent.

Related MCP server: image-viewer-mcp

Models (defaults, override via env)

Free (tried in order, 2 attempts each):

  • nvidia/nemotron-3.5-super-vl:free

  • google/gemma-4-31b-it:free

  • nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

  • google/gemma-4-26b-a4b-it:free

Cheap paid fallback (last resort, 3 attempts):

  • z-ai/glm-5.3-flash:floor

Free endpoints are rate-limited; the paid fallback guarantees an answer. Check current free models at https://openrouter.ai/models (filter input modality = image, price = 0).

Install

Option A — run from source (simplest)

git clone https://github.com/<you>/vision-mcp
cd vision-mcp
# no npm install needed (zero deps)
export OPENROUTER_API_KEY=sk-or-v1-...
node server.mjs

Option B — MCP client config

OpenCode (opencode.json / opencode.jsonc):

{
  "mcp": {
    "servers": {
      "vision": {
        "type": "local",
        "command": ["node", "/abs/path/to/vision-mcp/server.mjs"],
        "environment": {
          "OPENROUTER_API_KEY": "sk-or-v1-...",
          "VISION_MODELS": "nvidia/nemotron-3.5-super-vl:free,google/gemma-4-31b-it:free",
          "VISION_PAID_FALLBACK": "z-ai/glm-5.3-flash:floor"
        }
      }
    }
  }
}

Claude Desktop / Cursor / Cline use an equivalent mcpServers block (command + env). See .env.example for all options.

Configuration (environment)

Variable

Default

Meaning

OPENROUTER_API_KEY

— (required)

OpenRouter key

VISION_MODELS

nemotron,gemma-31b,…

comma-separated free models, in order

VISION_PAID_FALLBACK

(empty)

one cheap paid model tried last

VISION_ATTEMPTS

2

attempts per free model

VISION_PAID_ATTEMPTS

3

attempts for the paid fallback

VISION_TIMEOUT_MS

90000

per-attempt timeout

VISION_MAX_MB

20

max input image size

VISION_ALLOWED_DIR

(unset)

if set, local reads confined to this dir (+ OS temp)

OPENROUTER_BASE_URL

https://openrouter.ai/api/v1

API base

Security

  • The API key is read only from the environment — never bundled, never logged.

  • If VISION_ALLOWED_DIR is unset, the tool can read any local file path (it's a local dev tool). Set VISION_ALLOWED_DIR to sandbox it to a screenshots folder if you want to restrict reads.

  • Images are sent to OpenRouter (the model provider you select). Don't feed secrets/screenshots you wouldn't send to a third party.

Programmatic use (any MCP host)

The tool is standard MCP; the agent writes its own prompt per task (e.g. "harsh design review: layout, hierarchy, biggest problem, polish 1–5"). A ready-made design-review prompt lives in the Playgama skill (templates/vision-design-review-prompt.md).

License

MIT — see LICENSE.

Available Tools

1 tool
analyze_imageA

Get a text answer about an image using a vision model chain (free OpenRouter models first, then a cheap paid fallback, with retries). Use it when you cannot see the image yourself: UI/design review, OCR, "what is on this screenshot", comparing a render to an expectation. Pass a local file path or an http(s) URL. YOU write the prompt for your task. Returns { content, servedModel, attempts, tried }.

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

    Only one tool exists, so there is no possibility of misselection. Its purpose—answering an arbitrary prompt about an image via a vision model chain—is stated unambiguously, including accepted inputs (path or URL) and return shape.

    Naming Consistency4/5

    analyze_image follows a clean verb_noun snake_case convention, which is ideal. With a single tool there is no broader pattern to demonstrate consistency against, so it can't quite earn a 5.

    Tool Count4/5

    A single tool is genuinely sufficient here because the free-form prompt parameter makes it general-purpose (OCR, UI review, render comparison). It is narrowly scoped rather than trivial, though one tool offers no room for specialized conveniences like multi-image diffing.

    Completeness4/5

    The domain is 'get an answer about an image,' and the tool covers local paths, URLs, retries, and model fallback with diagnostic metadata returned. Minor gaps: no native multi-image/comparison mode and no way to configure or inspect the model chain, but the prompt-driven design lets agents work around these.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      C
      maintenance
      Provides an MCP tool that analyzes images from local paths, URLs, or data URLs via a vision language model, returning structured descriptions (brief, detailed, summary) so text-only LLMs can understand image content.
      -
    • A
      license
      A
      quality
      D
      maintenance
      Vision MCP enables text-only agents to understand images through any OpenAI-compatible vision model. It supports local images, URLs, screenshots, documents, charts, and code errors with tools like analyze_image and understand_image.
      2
      MIT