
Open Eagle Eye
Gives Claude direct access to live images from 32,000 public traffic and weather cameras across the US, Canada, Finland, Hong Kong, UK, and seven other countries. Cameras return JPEGs on plain HTTP GET requests, so there's no stream decoding or browser automation. The registry self-heals nightly with vision AI catching cameras that return error pages instead of live feeds. You get tools to fetch snapshots to disk, search by city or location, and add your own camera URLs locally before optionally submitting them upstream. Useful when you need real-time visual context about traffic conditions, weather, or street-level activity in major cities without hunting down individual DOT feeds.
- GitHub stars
- 4
- tools
- 9
- transport
- STDIO
- last updated
- Mar 31, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
get_snapshotFetch a live image from a camera — saves to disk, returns file path
Fetch a live image from a camera — saves to disk, returns file path
No parameter schema in public metadata yet.
list_camerasBrowse the registry with filters (city, location, category)
Browse the registry with filters (city, location, category)
No parameter schema in public metadata yet.
search_camerasSearch by name, location, or category
Search by name, location, or category
No parameter schema in public metadata yet.
add_local_cameraAdd a camera to your local collection
Add a camera to your local collection
No parameter schema in public metadata yet.
list_localShow your locally-added cameras
Show your locally-added cameras
No parameter schema in public metadata yet.
remove_localDelete a locally-added camera
Delete a locally-added camera
No parameter schema in public metadata yet.
submit_localShare local cameras upstream via GitHub issue
Share local cameras upstream via GitHub issue
No parameter schema in public metadata yet.
report_cameraReport a broken or low-quality camera
Report a broken or low-quality camera
No parameter schema in public metadata yet.
check_configShow API key configuration status
Show API key configuration status
No parameter schema in public metadata yet.
Sponsors
Readme
Open Eagle Eye
MCP server that gives AI agents instant access to public camera feeds worldwide. One HTTP GET, sub-second captures, no browser automation, no stream decoding.
Why
Most camera APIs require authentication, serve video streams, or hide images behind JavaScript rendering. Open Eagle Eye only indexes cameras that return a JPEG or PNG on a plain HTTP GET — the simplest possible integration. Agents don't need to render pages or decode video. They just fetch an image.
The registry is self-healing. A GitHub Action runs nightly, checks every camera, retries failures before removing them, and uses vision AI to catch cameras that return error pages instead of live feeds. Dead cameras get flagged automatically.
Quick start
{
"mcpServers": {
"openeagleeye": {
"command": "npx",
"args": ["-y", "openeagleeye"]
}
}
}
Or install globally:
npm install -g openeagleeye
openeagleeye
Details
- Repository
- github.com/stuchapin909/open-eagle-eye
- Package
openeagleeye- Transport
- STDIO
- Registry
- MCP registry, active