Skip to main content

Model Context Protocol (MCP)

Early Access

Try our newest feature! Only available through reach out. Contact us to join the early access program and get priority support.

Unizo offers an MCP server that integrates package and container registries with any LLM provider supporting the MCP protocol. This enables your AI agent to manage artifacts, analyze dependencies, and automate registry operations across Docker Hub, npm, PyPI, Maven Central, and other registry platforms via a single MCP server.

Supported Tools & Use Cases​

The following tools are available in the Packages and Container Registry MCP Server:

Tool NameDescription
list_repositoriesBrowse repositories, namespaces, and organizations in registries
search_artifactsSearch packages and containers by name, tags, or metadata
get_artifact_detailsRetrieve comprehensive artifact information including metadata and security data
list_tagsView available versions, tags, and releases for artifacts
analyze_dependenciesExamine package dependencies, vulnerabilities, and security issues
scan_imagePerform security scanning on container images

list_repositories​

Browse repositories, namespaces, and organizations in registries

Parameters:

  • integration: Target registry integration (required)
  • namespace: Organization or namespace to list
  • type: Repository type (container, package)
  • visibility: Filter by visibility (public, private)
  • page: Pagination control
  • limit: Number of results per page

search_artifacts​

Search packages and containers by name, tags, or metadata

Parameters:

  • integration: Target registry integration (required)
  • query: Search query (required)
  • type: Artifact type (container, npm, pypi, maven)
  • tags: Filter by tags or labels
  • include_deprecated: Include deprecated packages
  • sort: Sort order (relevance, updated, downloads)
  • limit: Maximum results to return

get_artifact_details​

Retrieve comprehensive artifact information including metadata and security data

Parameters:

  • integration: Target registry integration (required)
  • artifact: Artifact identifier (required)
  • version: Specific version (optional, latest if not specified)
  • include_vulnerabilities: Include vulnerability scan results
  • include_dependencies: Include dependency tree
  • include_sbom: Include software bill of materials

list_tags​

View available versions, tags, and releases for artifacts

Parameters:

  • integration: Target registry integration (required)
  • repository: Repository name (required)
  • include_signatures: Include signing information
  • include_digests: Include content digests
  • filter: Filter expression for tags
  • sort: Sort order (newest, oldest, semver)
  • limit: Maximum tags to return

analyze_dependencies​

Examine package dependencies, vulnerabilities, and security issues

Parameters:

  • integration: Target registry integration (required)
  • artifact: Artifact to analyze (required)
  • scan_type: Type of scan (security, license, quality)
  • depth: Dependency tree depth to analyze
  • include_transitive: Include transitive dependencies
  • severity_threshold: Minimum severity to report

scan_image​

Perform security scanning on container images

Parameters:

  • integration: Target registry integration (required)
  • image: Container image to scan (required)
  • scan_layers: Scan individual layers
  • check_base_image: Verify base image security
  • policy: Security policy to apply
  • include_fixes: Include available fixes

Installation​

Prerequisites​

  • A Unizo API key
  • An active PCR integration (Amazon ECR, Docker Hub, Google Artifact Registry, GitHub Container Registry, GitLab Container Registry, JFrog Artifactory, Microsoft ACR, Nexus)
  • Node.js v20 or higher

MCP Configuration​

Here is an example configuration for setting up the Unizo SCM MCP server:

{
  "mcpServers": {
    "unizo-pcr": {
        "command": "npx",
      "args": [
        "mcp-remote",
        "http://api.unizo.ai/mcp/pcr",
        "--allow-http",
        "--header",
        "apikey:${UNIZO_API_KEY}"
      ],
      "env": {
        "UNIZO_API_KEY": "your_api_key"
      }
    }
  }
}

Client Setup​

For detailed setup instructions with specific AI clients:

Environment Variables​

The following environment variables are required:

Error Handling​

All tools return errors in a consistent format:

{
  "error": {
    "code": "REPOSITORY_NOT_FOUND",
    "message": "Repository 'example/repo' not found"
  }
}

Common error codes:

  • INTEGRATION_NOT_FOUND: Invalid integration ID
  • REPOSITORY_NOT_FOUND: Repository doesn't exist or no access
  • ARTIFACT_NOT_FOUND: The specified package or image was not found
  • TAG_NOT_FOUND: Tag not found in repository
  • VULNERABILITY_SCAN_FAILED: Issue during vulnerability scan
  • RATE_LIMIT_EXCEEDED: API rate limit reached
  • UNAUTHORIZED: Invalid API key or insufficient permissions