OCI Registry
This MCP server provides tools for querying OCI registries and container image references, enabling AI assistants to retrieve image information, list repository tags, and access image manifests and configurations. Built by StacklokLabs using Go with the google/go-containerregistry library and mark3labs/mcp-go framework, it supports multiple authentication methods including bearer tokens, username/password, and Docker keychain integration, with configurable port settings and graceful shutdown handling. The implementation offers four core tools for getting image metadata (digest, size, architecture, OS, creation date, layers), listing available tags for repositories, retrieving raw image manifests, and accessing detailed image configurations, making it valuable for container security analysis, image inventory management, registry auditing, and any workflow requiring programmatic access to OCI registry data.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · 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/stackloklabs/ocireg-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve OCI Registry 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.