Skip to main content
Glama
odfalik

uthere

by odfalik
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

u there?

Camera-based presence detection for Claude Code. Uses your webcam to check if you're sitting at your computer.

Two components:

  1. MCP server exposes an is_user_present tool that Claude can call anytime to check if you're there

  2. Stop hook automatically keeps Claude working when you step away, so it doesn't stop and wait for input from an empty chair

Uses MediaPipe BlazeFace for fast, lightweight face detection. Works well with glasses, varied lighting, and different angles. The model (~200KB) is downloaded automatically on first run.

Install

Requires Python 3.11+ and uv.

git clone https://github.com/odfalik/uthere.git
cd uthere
uv sync

Camera permissions

On macOS, your terminal app needs camera access. Go to System Settings > Privacy & Security > Camera and enable it for your terminal (Terminal, iTerm2, etc).

Related MCP server: computer-use-mcp

Setup

Add either or both of the following to your Claude Code settings file (~/.claude/settings.json).

MCP server

Gives Claude a tool it can call to check if you're at your desk.

{
  "mcpServers": {
    "uthere": {
      "command": "uv",
      "args": ["--directory", "/path/to/uthere", "run", "python", "-m", "uthere.server"]
    }
  }
}

Stop hook

Prevents Claude from stopping when you're away. If Claude finishes a response and no face is detected, it gets a message telling it to keep going. A 60-second cooldown prevents infinite loops.

{
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "uv --directory /path/to/uthere run python -m uthere.hook",
            "timeout": 15
          }
        ]
      }
    ]
  }
}

Configuration

All configuration is through environment variables. Set them in your shell profile or in Claude Code's env settings.

Variable

Default

Description

UTHERE_AWAY_MESSAGE

"No face detected. User appears to be away..."

MCP tool message when no face is detected

UTHERE_PRESENT_MESSAGE

"User is at their computer."

MCP tool message when face is detected

UTHERE_HOOK_MESSAGE

"The user is not at their computer right now..."

Message sent to the agent when the stop hook blocks

Example using Claude Code's env settings:

{
  "env": {
    "UTHERE_AWAY_MESSAGE": "User is away. Send them a message on Discord.",
    "UTHERE_HOOK_MESSAGE": "User is AFK. Keep working, ping them on Discord if stuck."
  }
}

How it works

  1. Opens the webcam via OpenCV

  2. Takes a few warmup frames (lets auto-exposure settle)

  3. Checks 3 consecutive frames with BlazeFace face detection

  4. Returns true if a face is found in any frame

The whole check takes about 1-2 seconds. The camera is released immediately after each check.

License

MIT

Available Tools

1 tool
is_user_presentA

Check if the user is sitting at their computer by detecting a face via the webcam.

Returns {"present": true/false} with an explanatory message. If the camera cannot be accessed, returns an error message.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description conveys key behavioral traits: it uses the webcam for face detection, returns a structured JSON with a 'present' field and an explanatory message, and handles camera access errors by returning an error message. This is detailed for a simple read-only check, though it does not mention potential privacy implications or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, consisting of two short paragraphs and only three sentences. Every sentence contributes essential information: what the tool does, what it returns, and its error behavior. There is no redundancy or filler, making it well-structured and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (no parameters, no annotations, no output schema), the description covers the essential aspects: the action, the return format, and error handling. It is sufficiently complete for an agent to understand and invoke the tool correctly. Minor additional details like a note on webcam privacy could improve it, but they are not necessary for basic operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the rubric sets a baseline of 4 for such cases. The description correctly omits parameter details since there are none, and it does not need to compensate for schema gaps. The description simply adds meaningful context about the tool's operation without needing to explain parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Check if the user is sitting at their computer by detecting a face via the webcam.' It includes a specific verb ('check'), a resource ('user presence'), and the method ('detecting a face via webcam'), making it distinct and unambiguous. Although no siblings are listed, the description would differentiate from any related tool by specifying the face-detection approach.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context by explaining that the tool detects user presence via webcam, which implies when it should be used. It also notes error behavior when the camera is inaccessible, providing an implicit caveat. However, it does not explicitly state scenarios where this tool should be avoided or alternatives, but with no sibling tools, that is not a major gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of overlap or confusion between tools. The tool's purpose is clearly distinct.

Naming Consistency5/5

The single tool name 'is_user_present' follows a clear verb_noun pattern, which is consistent and predictable. There are no other tools to cause inconsistency.

Tool Count3/5

With only one tool, the server feels very thin. It is borderline appropriate for a narrowly scoped purpose, but it lacks the richness expected of a full tool set.

Completeness4/5

The tool covers the core presence-check functionality well, but there are minor gaps such as no configuration or status reporting options. Overall, the surface is mostly complete for its stated purpose.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • device-controller-mcp

    geojakes
    A
    license
    Not graded
    quality
    B
    maintenance
    An MCP server that lets Claude Desktop and Claude Code control your PC — take screenshots, click, type, manage windows, and more.
    MIT

  • computer-use-mcp

    domdomegg
    A
    license
    Not graded
    quality
    A
    maintenance
    MCP server that enables Claude to control your computer, similar to Anthropic's computer use but easy to set up locally.
    327
    356
    MIT

  • realhands

    kanishka089
    A
    license
    Not graded
    quality
    A
    maintenance
    An MCP server that lets Claude operate your real computer by moving the actual mouse, clicking, typing, and reading the actual screen, working with your own logged-in sessions in any application.
    MIT

  • mcp-control

    andrefigueira
    A
    license
    Not graded
    quality
    D
    maintenance
    MCP server that gives Claude Code full mouse, keyboard, and app control on macOS. Tell Claude what to do and watch it operate your computer.
    140
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/odfalik/uthere'

If you have feedback or need assistance with the MCP directory API, please join our Discord server