MCP.Market

ocular MCP server

by xyun1996·io.github.xyun1996/ocular·v0.1.0
No reviews yet

Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

0 stars57 downloads/wk

Reviews

Write one

Nobody has reviewed ocular yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

ocular tools (8, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • analyze_chart_image

    Analyze a chart image and return labels, trends, approximate values, and limitations.

  • analyze_image

    Analyze a general image and return structured JSON for a coding agent.

  • analyze_ui_screenshot

    Analyze a webpage, app, UI, or design mockup screenshot for frontend implementation work.

  • compare_ui_screenshots

    Compare two UI screenshots and return implementation-useful visual differences.

  • create_upload_sessionwrite action

    Returns upload instructions for the binary side channel (use this to analyze LOCAL image files without base64 corruption). Before uploading, verify the local file exists and is non-empty with Bash (e.g. `ls -la <path>` or `test -f <path> && stat -c %s <path>`). Then PUT the raw bytes to the returned upload_url with curl --data-binary (NOT base64); the response gives a file_id to pass to any vision

  • diagnose_error_screenshot

    Analyze error, terminal, console, browser, or build failure screenshots.

  • extract_table_from_image

    Extract visible table data from an image as structured JSON, Markdown, or CSV-oriented output.

  • extract_text_from_image

    Extract OCR text from screenshots, documents, tables, terminal output, or code images.

Public scan report

scanner v0.1.10 · 2026-11-04 · same rubric, same numbers if you re-run it

no findings
  • Code scan34 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 20 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How ocular compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 65% of 48,255 servers
Tools
8
the typical server has 7
Tools that change things
13%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
57
more than 47% of 12,191 servers with a package

What its tools let an agent do: 7 read · 1 create

Install ocular in Claude Code, Cursor or VS Code

Runs npx -y ocular-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add ocular -- npx -y ocular-mcp
Add to Cursor

What the publisher says

From the ocular repository's README, as published. We do not edit it. Read it on GitHub

ocular

Vision for coding agents.

ocular is an MCP server that lets text-first coding agents analyze screenshots, UI mockups, terminal errors, documents, tables, and charts through OpenAI-compatible vision models.

It is designed for both local stdio use and remote HTTP deployments. For remote agents, image bytes can travel through a binary upload side channel while MCP tool calls carry only a lightweight file_id, avoiding large inline base64 payloads.

Project status: early-stage and actively evolving. Feedback, bug reports, integrations, and real-world usage reports are welcome.

Why ocular?

Coding agents are good at reading source code but often lose context when the important evidence is visual: a broken layout, a terminal screenshot, an error dialog, a chart, or a design reference.

ocular turns those visual inputs into structured data an agent can reason about.

  • Agent-oriented output — tools return structured JSON instead of prose-only descriptions.
  • 8 focused vision tools — general analysis, OCR, UI inspection, error diagnosis, UI comparison, table extraction, chart analysis, and upload orchestration.
  • OpenAI-compatible provider interface — point ocular at a compatible multimodal endpoint and model; reproducibly tested configurations are tracked in Provider compatibility.
  • Remote-friendly uploads — binary PUT /upload flow for large images with content-addressed file_id references.
  • Local or remote MCP — stdio for local clients, HTTP for hosted/private deployments.
  • Caching and persistence — deduplicated uploads plus result caching for repeated agent workflows.

How it works

flowchart LR
    A[Coding agent] -->|MCP tool call| B[ocular]
    C[Image / screenshot] -->|binary upload or base64| B
    B -->|OpenAI-compatible request| D[Vision model]
    D -->|multimodal response| B
    B -->|structured JSON| A

For remote HTTP deployments, the recommended path is:

image bytes -> PUT /upload -> file_id -> MCP vision tool -> structured result

See Architecture for the upload and caching model.

Demo

Want to see the full handoff from screenshot to coding-agent evidence? Read the end-to-end demo.

It walks through a remote image upload, a diagnoseerrorscreenshot call, the structured fields returned to the agent, and how that evidence is combined with repository context. Example model output is explicitly marked representative rather than presented as a benchmark.

Quick start

1. Install

The published npm package is ocular-mcp. It installs the CLI command ocular.

Global install:

npm install -g ocular-mcp

Or run it without a global install:

npx -y ocular-mcp

To build from source instead:

git clone https://github.com/xyun1996/ocular.git
cd ocular
npm install
npm run build

2. Configure a vision provider

ocular requires an OpenAI-compatible multimodal endpoint, API key, and model name:

OCULAR_BASE_URL=https://your-openai-compatible-endpoint.example/v1
OCULAR_API_KEY=your_api_key
OCULAR_MODEL=your_vision_model

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

ocular: common questions

Is ocular MCP server safe?
Mostly: it is graded B (83/100). Read the ocular safety report
How do I install ocular?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does ocular need an API key?
Yes. The registry entry asks for OCULAR_API_KEY.
Is ocular maintained?
The last commit was 20 days ago (2026-10-15). The latest release is v0.1.0.
How does ocular compare with other MCP servers?
safety score 83/100 (higher than 65% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 13% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.