OpenZIM
This OpenZIM MCP server by Cameron Rye enables AI models to access and search ZIM format knowledge bases offline, providing tools for listing ZIM files, searching content with configurable limits and offsets, and retrieving specific entries with smart fallback mechanisms. Built with Python and featuring a modular architecture with comprehensive security validation, intelligent caching with LRU eviction and TTL support, and HTML content processing with BeautifulSoup, it offers robust path validation to prevent directory traversal attacks, instance tracking to prevent configuration conflicts, and automatic path mapping for reliable entry retrieval. The implementation includes extensive testing coverage, performance benchmarks, and development tooling with pre-commit hooks, making it ideal for researchers and developers who need AI-assisted access to offline Wikipedia dumps, educational content archives, and other ZIM-formatted knowledge repositories without requiring internet connectivity.
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
- security
- Source
- PulseMCP
- Repository
- github.com/cameronrye/openzim-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve OpenZIM 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.