MCP Webcam is a server that provides access to your webcam through the Model Context Protocol (MCP). It allows you to capture images from your webcam or take screenshots, making these available to AI assistants like Claude. The server supports multiple users in streaming mode and offers sampling functionality for multi-modal interactions.
For STDIO mode:
npx @llmindset/mcp-webcam
To use a custom port:
npx @llmindset/mcp-webcam 9999
For Streaming HTTP mode:
npx @llmindset/mcp-webcam --streaming
Docker runs in streaming mode by default:
docker run -p 3333:3333 ghcr.io/evalstate/mcp-webcam:latest
Customize your deployment with these environment variables:
MCP_TRANSPORT_MODE
- Set to stdio
for STDIO mode (default: streaming
)PORT
- The port to run on (default: 3333
)BIND_HOST
- Network interface to bind to (default: localhost
)MCP_HOST
- Public-facing URL (default: http://localhost:3333
)# STDIO mode
docker run -p 3333:3333 -e MCP_TRANSPORT_MODE=stdio ghcr.io/evalstate/mcp-webcam:latest
# Custom port
docker run -p 8080:8080 -e PORT=8080 ghcr.io/evalstate/mcp-webcam:latest
# Cloud deployment with custom domain
docker run -p 3333:3333 -e MCP_HOST=https://your-domain.com ghcr.io/evalstate/mcp-webcam:latest
To connect with fast-agent:
uvx fast-agent-mcp go --url http://localhost:3333/mcp
For STDIO mode, add this to your fastagent.config.yaml
:
webcam_local:
command: "npx"
args: ["@llmindset/mcp-webcam"]
VSCode (version 1.101.0+) supports MCP Sampling:
http://localhost:3333/mcp
as an MCP Server in VSCodeClaude Desktop doesn't support Sampling but can use mcp-webcam. Add this to the mcpServers
section in claude_desktop_config.json
:
"webcam": {
"command": "npx",
"args": [
"-y",
"@llmindset/mcp-webcam"
]
}
Once connected:
http://localhost:3333
(or your custom port)With Claude Desktop, you can ask:
For screenshots, navigate to the browser window you want to capture before Claude's request comes in.
In Streaming mode, you can enable multi-user support:
MCP_HOST
environment variable to your hostnameYou can also try the public demo at https://evalstate-mcp-webcam.hf.space/ and specify your own UserID with ?user=<YOUR_USER_ID>
parameter.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.