ocular
Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.
MCP server · by xyun1996
About
ocular is an MCP server published by xyun1996. Marketplaces we read that list it: 1 (Official MCP Registry). We first saw it on 2026-10-11 and have recorded no change since. As of our marketplace pass on 2026-10-13.
What it asks for
- Runs on your machine
- Secrets: 1
- Settings: 3
Requires: OCULAR_API_KEY (secret), OCULAR_BASE_URL, OCULAR_MODEL
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a local MCP server: npm package
Built from what Official MCP Registry declares.
claude mcp add --env "OCULAR_API_KEY=<YOUR_OCULAR_API_KEY>" --env "OCULAR_BASE_URL=<YOUR_OCULAR_BASE_URL>" --env "OCULAR_MODEL=<YOUR_OCULAR_MODEL>" --transport stdio ocular -- npx -y ocular-mcp[mcp_servers.ocular]
command = "npx"
args = ["-y", "ocular-mcp"]
[mcp_servers.ocular.env]
OCULAR_API_KEY = "<YOUR_OCULAR_API_KEY>"
OCULAR_BASE_URL = "<YOUR_OCULAR_BASE_URL>"
OCULAR_MODEL = "<YOUR_OCULAR_MODEL>"{
"mcpServers": {
"ocular": {
"command": "npx",
"args": [
"-y",
"ocular-mcp"
],
"env": {
"OCULAR_API_KEY": "<YOUR_OCULAR_API_KEY>",
"OCULAR_BASE_URL": "<YOUR_OCULAR_BASE_URL>",
"OCULAR_MODEL": "<YOUR_OCULAR_MODEL>"
}
}
}
}Replace the values in angle brackets with your own. We show the names of the settings, never values.
Where it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Official MCP Registry (Open the registry record) | Listed | 0.1.0 | Forks (GitHub): 0 Stars (GitHub): 0 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
What changed
Nothing has moved on this plugin since we started watching it.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
uisight io.github.yusufcemres/uisight
Your AI sees the screen but can't measure it — measured web UI findings, shared live sessions
-
macos-vision-mcp io.github.woladi/macos-vision-mcp
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
-
MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
-
ui-debugger-mcp io.github.developerz-ai/ui-debugger-mcp
Autonomous UI debugging MCP server: an agent drives the browser/desktop, reports bugs + UX issues.
-
Desktop UI automation for AI agents: verified clicks, wait_for, batch, UI Automation, OCR
-
one-shot-ui io.github.TN0123/one-shot-ui
Deterministic UI extraction and screenshot diffing for AI coding agents.
-
can-see io.github.HurleySk/can-see
Let AI agents see and interact with terminal/CLI apps via PNG screenshots
-
mcp io.github.noncelogic/mcp
Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
-
pixelcheck io.github.xcodethink/pixelcheck
Real eyes and hands on the web for AI agents. MCP-first. Local-first. Vendor-agnostic.
-
Captured web interfaces, screenshots, flows and structured evidence for AI coding agents.
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
Give Claude Code the ability to see running web applications. Visual Eyes captures screenshots via Playwright, lets Claude analyze the UI visually, auto-fix layout bugs, and run…
-
Agent skills for Meticulous visual regression testing — review test runs, investigate replays, debug diffs. Also connects the hosted Meticulous MCP server.
-
Your agent writes the code. Subtext proves it works. MCP tools for verification — persistent knowledge of your app, real-browser checks, and session replays your team can watch…
-
Autonomous automation agent for Claude Code with 20 specialized MCP tools (Playwright web control, filesystem, macOS native via PyAutoGUI, AppleScript, shell), intelligent model…
-
A Claude Code plugin that captures focused screenshots of specific UI components from a running browser with a red rectangle marking the exact element, and uses them for visual…
Has a listing on Claude Code: claude-plugins-official (5)
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
MCP server for terminal commands, file operations, and process management
-
MCP server for Chrome DevTools
-
mcp-server io.github.cap-js/mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications.
Has a listing on Claude: knowledge-work-plugins (5)
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
MCP server for terminal commands, file operations, and process management
-
Give Claude a real browser — your Chrome or a Browser Use Cloud browser. Use it whenever a task involves a website or web app: browsing, scraping and data extraction, filling…
-
Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
-
Keep your coding agent up to date with the latest web best practices
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Test Android apps with emulator workflows for reproduction, screenshots, UI inspection, log capture, and performance profiling.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Use MagicPath to find, inspect, install, create, and edit UI components from Codex.
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build iOS apps with workflows for App Intents, SwiftUI UI work, Simulator mirroring in the Codex in-app browser, performance profiling, leak investigation, and simulator debugging.
Has a listing on Community GitHub marketplaces (5)
-
MCP server for terminal commands, file operations, and process management
-
Let any AI agent operate desktop apps on macOS, Windows and Linux, in the background and safely.
-
MCP server for Chrome DevTools
-
Give Claude a real browser — your Chrome or a Browser Use Cloud browser. Use it whenever a task involves a website or web app: browsing, scraping and data extraction, filling…
-
inquisitor io.github.1111111111111111111114oLvT2/inquisitor
Hypothesis-driven problem solving for AI agents: probe, falsify, escalate.
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
Record your screen doing a manual process, drop the video on your Desktop, and let Copilot CLI analyze it frame-by-frame to build working automation scripts. Supports narrated…
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Capture, annotate, and embed screenshots and animated GIF demos in pull request descriptions. Includes Playwright-based UI capture, PIL image annotations, PR embedding workflows…
-
MCP server for Chrome DevTools
-
Safe BLE diagnostics, evidence workflows, and guarded automation for AI agents.
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
code-apps-preview
Build and deploy Power Apps code apps using React, Vite, and Power Platform connectors.
Has a listing on Cursor: cursor/plugins (5)
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
Build apps, scripts, and automations with the TypeScript SDK.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Browse and automate the web with TinyFish: run multi-step web automations, search the web, extract clean page content, and drive remote stealth browser sessions.
-
Render PR diffs as review canvases grouped by importance.
Has a listing on Docker MCP Catalog (5)
-
mcp-server-browserbase io.github.browserbase/mcp-server-browserbase
MCP server for AI web browser automation using Browserbase and Stagehand
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
-
A MCP server implementation for hyperbrowser.
-
MCP server for terminal commands, file operations, and process management
-
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
Has a listing on Official MCP Registry (5)
-
uisight io.github.yusufcemres/uisight
Your AI sees the screen but can't measure it — measured web UI findings, shared live sessions
-
macos-vision-mcp io.github.woladi/macos-vision-mcp
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
-
MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
-
ui-debugger-mcp io.github.developerz-ai/ui-debugger-mcp
Autonomous UI debugging MCP server: an agent drives the browser/desktop, reports bugs + UX issues.
-
Desktop UI automation for AI agents: verified clicks, wait_for, batch, UI Automation, OCR
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Is this your plugin?
Add it to your projects and prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.