- Update documentation with directory_tree declaration
- Add excludePatterns parameter to DirectoryTreeArgsSchema
- Implement pattern exclusion in buildTree function using minimatch
- Pass excludePatterns through recursive calls
- Support both simple and glob patterns for exclusion
- Maintain consistent behavior with search_files implementation
* Add tests and fix implementation
---------
Co-authored-by: Ola Hungerford <olahungerford@gmail.com>
Co-authored-by: Adam Jones <adamj+git@anthropic.com>
Co-authored-by: Adam Jones <adamj@anthropic.com>
Previously resources were generated as 50 text resources followed by 50 blob resources.
Now they alternate: Text, Blob, Text, Blob, etc. This provides better variety
when using tools like getResourceLinks and maintains the useful interleaving
pattern that was present before the UUID-based refactor.
Co-authored-by: Ola Hungerford <olaservo@users.noreply.github.com>
Voice MCP has been renamed to Voice Mode. This updates:
- Name from 'Voice MCP' to 'Voice Mode'
- GitHub URL from voice-mcp to voicemode
- Website from voice-mcp.com to voicemode.ai
Add mcp-memory-service to the Third-Party Servers section in alphabetical order. This universal memory service provides semantic search, persistent storage, and autonomous memory consolidation for AI assistants across multiple platforms.
Add MCP Context Provider to the Third-Party Servers section in alphabetical order. This server provides AI models with persistent tool-specific context and rules, preventing context loss between chat sessions.
Implements @domdomegg's proposal to use UUIDs for resource identification instead of array indices:
- Generate UUIDs for all 100 resources (50 text, 50 blob)
- Use semantic paths: test://static/resource/text/{uuid} and test://static/resource/blob/{uuid}
- Remove dependency on array indices for URI construction
- Update resource templates to reflect new URI patterns
- Modify getResourceReference tool to accept resourceUri instead of resourceId
- Update resource_prompt argument from resourceId to resourceUri
- Improve resource link descriptions to mention UUID-based identification
- Update README documentation to reflect UUID-based system
This eliminates the confusion between array indices (0-based) and URI numbers (1-based)
while providing more intuitive resource categorization through semantic paths.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: adam jones <domdomegg@users.noreply.github.com>
Added fast-filesystem-mcp to the Community Servers section.
This enterprise-grade filesystem MCP server provides.
- Advanced filesystem operations with Claude optimization
- Large file handling with streaming capabilities
- Sequential reading with continuation tokens
- Comprehensive directory operations and file search
- Enterprise-grade stability with overflow protection
- Automatic backup and recovery features
Repository: https://github.com/efforthye/fast-filesystem-mcp
NPM: https://www.npmjs.com/package/fast-filesystem-mcp
Follows alphabetical order in Community Servers section.
- Add CIViC MCP server for clinical variant interpretation
- Add DataCite MCP server for research data and publication metadata
- Add DGIdb MCP server for drug-gene interaction data
- Add Entrez MCP server for NCBI biomedical databases
- Add NCI GDC MCP server for cancer genomic data
- Add OpenNeuro MCP server for open neuroimaging datasets
- Add Open Targets MCP server for target-disease associations
- Add Pharos MCP server for target, drug, and disease information
- Add RCSB PDB MCP server for 3D protein structures
- Add UniProt MCP server for protein sequence and functional data
- Add Wikidata SPARQL MCP server for structured knowledge queries
- Add ZincBind MCP server for zinc binding sites in proteins
All servers added in alphabetical order following contribution guidelines.
