OpenEye
Vision for agents: run YOLO, depth, segmentation and detection models locally or via hosted API.
Open the source (opens github.com) https://github.com/aw3-technology/openeye.sh
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: OPENEYE_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.aw3-technology.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
openeye-sh@0.3.0
From the server's entry in the official MCP Registry
Settings it asks for
OPENEYE_API_KEYsecret · Key from https://openeye.sh/dashboard/settings/api-keys; only needed for the hosted openeye_api_* tools.
Related
-
openeye
MCP serversProcedure verification for AR/XR with memory, visual sessions, and DPO trajectory export.
@dumbspacecookie/openeye@0.1.1 -
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.
-
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.
-
Connect MCP servers to Claude Code
MCP serversAnthropic's guide to adding MCP servers to Claude Code, with examples of local and remote servers.