EPICS
EPICS MCP server that provides AI assistants with direct access to EPICS (Experimental Physics and Industrial Control System) Process Variables through the PyEPICS library, supporting both stdio and SSE transport protocols. The implementation offers three core tools for getting PV values, setting PV values, and retrieving PV metadata, with comprehensive error handling for network timeouts and connection issues. Built with Docker support and Smithery configuration, it enables AI-assisted control system monitoring and automation workflows for scientific facilities, industrial automation, and laboratory equipment management where conversational interfaces need programmatic access to EPICS-controlled devices and sensors.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/eunsang284/epics-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve EPICS from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.