mcpbeat Sign in

NIRA Screen Vision MCP Server

local only

NIRA Screen Vision MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 49 installs a week from pypi.

Real-time screen capture + AI vision for Claude — see, analyze, and OCR your screen

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 22 · avg 6 · +14% w/w
a month agotoday
49
Installs / week
pypi · nira-screen-vision
Stars
on GitHub
Last commit
0 releases in 90 days
License
language unknown

This one has been quiet for a while

Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add nira-screen-vision -- uvx nira-screen-vision
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "nira-screen-vision": {
      "args": [
        "nira-screen-vision"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.nira-screen-vision]
command = "uvx"
args = ["nira-screen-vision"]
.cursor/mcp.json
{
  "mcpServers": {
    "nira-screen-vision": {
      "args": [
        "nira-screen-vision"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "nira-screen-vision": {
      "args": [
        "nira-screen-vision"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: ANTHROPIC_API_KEY (Anthropic API key for AI vision analysis). The author declared them in the registry entry; get the values from the project itself.

Alternatives to NIRA Screen Vision MCP

same job, measured the same way
I
Stashot
by tammifull

Capture, OCR-search, and retrieve local Mac screenshots for AI agents through Stashot.

15 installs/wk local only
Contendeo
by contendeo

Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.

answering
Ocular Audio MCP
by rayakaan

MCP server for video transcripts, screenshots, and OCR on YouTube and web videos.

44 installs/wk local only
Visiongemma
by q1023884985

Local AI vision MCP server for Windows: OCR, chart analysis, scene description. 100% offline.

78 installs/wk local only
TinkyVision
by agewellepm

Screen observation, OCR and permission-controlled app input over MCP for Apple silicon Macs.

local only
Screen Control
by xeakaes

Safety-gated computer use for AI agents: screen OCR and vision, mouse, keyboard, window control.

local only
Claude KVM
by aras-workspace

MCP server — control remote desktops via VNC with a native Swift daemon and Apple Vision OCR

95 installs/wk local only
Groupdocs Comparison MCP
by groupdocs-comparison

MCP server for GroupDocs.Comparison — compare, analyze, and inspect documents via AI agents.

local only

NIRA Screen Vision MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for NIRA Screen Vision MCP?
NIRA Screen Vision MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package nira-screen-vision was installed 49 times last week.
Is NIRA Screen Vision MCP still maintained?
The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
How do I connect NIRA Screen Vision MCP?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls nira-screen-vision straight from pypi; nothing to host, nothing to sign up for.
How many people use NIRA Screen Vision MCP?
The pypi package nira-screen-vision was installed 49 times in the last week. Week over week that is +14%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.