Log inSubmit server
Ocular logo

Ocular

Analyzes screenshots, UI layouts, errors, tables, and charts for coding agents through OpenAI-compatible vision models.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Ocular

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "ocular": {
      "command": "npx",
      "args": [
        "-y",
        "ocular-mcp"
      ],
      "env": {
        "OCULAR_BASE_URL": "YOUR_VALUE_HERE",
        "OCULAR_API_KEY": "YOUR_VALUE_HERE",
        "OCULAR_MODEL": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 8 tools correctly (5d ago).

Overview

The ocular MCP server gives coding agents structured vision tools for screenshots, UI mockups, terminal errors, documents, tables, and charts. It sends image data to an OpenAI-compatible multimodal endpoint and returns JSON-oriented results through MCP. Local clients can use stdio, while remote deployments can upload image bytes and pass a lightweight file ID to vision tools. Reach for it when an agent needs visual evidence for debugging, OCR, UI review, comparison, or data extraction.

Use cases

  • Diagnose terminal or browser errors from screenshots
  • Review implemented interfaces for layout and accessibility issues
  • Compare reference and rendered UI screenshots
  • Extract text, tables, or chart data from images

Key features

  • Structured image analysis
  • Layout-aware OCR
  • UI screenshot review
  • Screenshot error diagnosis
  • Table and chart extraction
  • Local stdio and remote HTTP transports

Tools8

What Ocular lets your agent do. Expand a tool for its parameters.

Verified live~1.8k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

4/4 checks healthy over the last 28d

What it can do

From the 8 tools this server returned when we ran it.

Runs commands · 3Read-only tools · 5
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age68 days
Maintainers1

Observed 2026-10-19 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 9d ago via OSV.dev · ocular-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads96Package downloads in the last 30 days.
Last commit10d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed8Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Ocular works

What ocular MCP server does

The ocular MCP server connects text-first coding agents with OpenAI-compatible multimodal vision models. It converts visual inputs into structured results that an agent can use alongside repository and project context. Supported inputs include screenshots, interface mockups, terminal or browser error captures, documents, tables, and charts.

The server exposes eight MCP tools. General image analysis handles broad inspection, while specialized tools target OCR, UI review, error diagnosis, screenshot comparison, table extraction, chart interpretation, and remote upload setup. Outputs are intended for agent workflows rather than prose-only image descriptions.

How it works

A client sends an MCP tool request to ocular with either a file_id or, where supported for local use, inline base64 image data. The server packages the image and request for an OpenAI-compatible vision endpoint, then returns the model result as structured JSON.

For remote operation, the recommended sequence is to upload raw image bytes with an HTTP PUT /upload request. The upload produces a content-addressed file_id, which the client supplies to a later vision-tool call. This keeps large image payloads out of the MCP request itself. Uploads can be deduplicated, and result caching is available for repeated workflows.

The server supports stdio for locally launched MCP clients and HTTP transport for hosted or private deployments. HTTP mode can use an authentication token and configurable host, port, and path settings.

Setup and configuration

Install the published ocular-mcp package globally with npm, run it through npx, or build the repository from source. The project requires Node.js 20 or newer. A normal local launch uses the ocular command and communicates over standard input and output.

The ocular MCP server requires three provider settings: OCULAR_BASE_URL for the OpenAI-compatible API endpoint, OCULAR_API_KEY for authentication, and OCULAR_MODEL for the vision-capable model name. Optional settings control provider headers, temperature, token limits, timeouts, image-size limits, caching, upload storage, and the public upload URL.

For HTTP deployments, set MCP_TRANSPORT=http and configure the host, port, path, and authentication variables as needed. Remote clients also need access to the upload endpoint when using the binary upload flow.

Tools and capabilities

  • analyze_image performs general structured image inspection.
  • extract_text_from_image extracts text while considering reading order and layout.
  • analyze_ui_screenshot reviews hierarchy, spacing, typography, and accessibility concerns.
  • diagnose_error_screenshot extracts and analyzes terminal, browser, or build errors.
  • compare_ui_screenshots compares a reference image with an implementation image.
  • extract_table_from_image turns visible table content into structured data.
  • analyze_chart_image examines labels, values, trends, and uncertainty.
  • create_upload_session provides upload details for remote clients.

Limitations and notes

The server depends on an OpenAI-compatible multimodal endpoint and a model that supports vision. Compatibility is specific to the endpoint and model combination; the project documents smoke-tested configurations rather than treating API compatibility as automatic.

The project is described as early-stage and actively evolving. Vision results depend on the selected provider and model, and the included benchmark measures execution, JSON structure, and timing rather than broad model quality. Avoid placing long-lived provider keys directly in shared shell history; use the MCP client’s environment or secret-management features when available.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Ocular

ocular is an MCP server that connects coding agents to OpenAI-compatible multimodal vision endpoints and provides tools for image analysis, OCR, UI screenshot review, error diagnosis, screenshot comparison, table extraction, chart analysis, and remote upload setup through structured JSON results.

Install it with npm using `npm install -g ocular-mcp`, or run it without a global installation through `npx -y ocular-mcp`. You can also clone the repository, install dependencies, and build it from source.

Set `OCULAR_BASE_URL`, `OCULAR_API_KEY`, and `OCULAR_MODEL`. These identify the OpenAI-compatible multimodal endpoint, provider credential, and vision-capable model. Additional variables configure HTTP transport, caching, uploads, limits, and provider-specific headers.

Yes, ocular provides a standard MCP interface that can be configured in MCP clients such as Cursor. The README gives a generic MCP configuration pattern and a specific Claude Code example; the client must also provide the required environment variables.

Remote deployments can accept image bytes through `PUT /upload` and return a content-addressed `file_id`. Pass that identifier to a vision tool instead of sending a large base64 image through MCP. HTTP authentication can be configured for the upload endpoint.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOcular AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/ocular?style=directory)](https://allmcps.com/mcp/ocular)
HTML Embed
<a href="https://allmcps.com/mcp/ocular"><img src="https://allmcps.com/api/badge/ocular?style=directory" alt="Ocular on AllMCPs" /></a>