Enhanced

• Enhanced tool descriptions with parameter details in mcp_description method
  • Added support for displaying parameter descriptions from schema definitions
  • Improved formatting with hyphen separator for better readability
  • Updated tests to verify parameter descriptions are properly included
  • Makes tool descriptions more informative for Claude

Fixed

• Fixed pytest configuration by adding asyncio_default_fixture_loop_scope setting
  • Added explicit configuration in pyproject.toml to address deprecation warnings
  • Set asyncio mode to "strict" for more reliable async tests

Documentation

• Added project_info section to system prompt template
  • Includes repository name and owner details for better context
  • Improves system's ability to generate accurate project-specific responses

Changed

• Removed outdated TODO comment in agent tool registration
• Updated .gitignore to exclude aider files and CLAUDE.md

Added

• Added new USEFUL_PROMPTS.md document with practical prompt templates for common scenarios:
  • Summarizing history for continued conversations
  • Automation research summaries
  • Release preparation commands
  • Resuming interrupted conversations

Changed

• Reduced default values for agent tool limits:
  • agent_max_iterations reduced from 30 to 10
  • agent_max_tool_uses reduced from 100 to 30
• Enhanced system prompt documentation for the dispatch_agent tool:
  • Improved guidelines for when to use the dispatch_agent tool
  • Added detailed examples for effective agent prompting
  • Clarified agent limitations and capabilities
  • Added categorized use case recommendations

Documentation

• Improved README.md with clearer feature descriptions
• Fixed formatting and alignment in README.md tables
• Added cross-reference to USEFUL_PROMPTS.md in the README
• Added specific guidance for file reading operations in system prompt

Added

• Added Agent Tool for task delegation and concurrent execution
  • Agent Tool enables Claude to delegate complex tasks to specialized sub-agents that can work in parallel, enhancing performance for complex operations like code search, analysis, and multi-step tasks
  • Agents use read-only tools to ensure safety while maintaining full access to information retrieval capabilities
  • Introduced new parameter --enable-agent-tool to allow users to control whether the agent tool is registered
  • Added parameters --agent-max-iterations (default: 30) and --agent-max-tool-uses (default: 100) to control agent behavior
  • Implemented multi-agent support to enable concurrent sub-agent execution for improved performance when handling multiple related tasks
  • Agents return results that are automatically formatted and integrated into Claude's responses
• Added LiteLLM integration to support various model providers beyond OpenAI
  • Command line support for specifying the model name, API key, and token limits
  • Support for Anthropic, OpenAI, Google, and other LLM providers
  • Simplified configuration through environment variables or command-line arguments

Enhanced

• Enhanced system prompt with best practices and dispatch agent usage guidelines
• Improved agent tool implementation with better parameter validation and error handling
• Increased max_tool_uses limit from 15 to 30 for improved agent flexibility
• Optimized agent implementation to avoid redundant checks and improve performance

Changed

• Restricted agent tool to use only read-only variants of filesystem tools for security
• Simplified agent tool implementation to focus on multi-agent operation
• Refactored system prompt handling and improved user prompt support
• Updated parameter validation to support both string and array inputs for prompts

Fixed

• Fixed JSON serialization error in agent tool error handling
• Fixed redundant type checks and improved test environment handling
• Improved path description in read_files schema for better clarity
• Updated type annotations to use built-in generics syntax

Documentation

• Added detailed documentation for the agent tool in INSTALL.md, explaining setup and configuration options
• Added debugging guide for Model Context Protocol Inspector
• Updated installation instructions with LLM model and token configuration options
• Clarified cwd parameter restrictions in shell tool documentation

Enhanced

• Significantly improved performance of search_content and content_replace tools
• Implemented parallel processing for file searching with batched execution
• Optimized file finding strategy using more efficient directory traversal
• Added semaphore-based concurrency control to avoid overwhelming the system

Changed

• Replaced recursive directory traversal with more efficient pathlib.Path.rglob() method
• Restructured file search logic to filter allowed paths more efficiently
• Changed file pattern matching to use fnmatch for more consistent behavior

Enhanced

• Enhanced search_content tool to use regular expression pattern matching instead of simple substring matching
• Added comprehensive test suite for regex search functionality
• Improved code search capabilities with pattern matching support

Changed

• Modified search implementation to use re.search() instead of the in operator
• Maintained backward compatibility with existing string search patterns

Added

• Added Jupyter notebook support with read_notebook and edit_notebook tools
• Implemented reading of notebook cells with their outputs (text, error messages, etc.)
• Added capabilities for editing, inserting, and deleting cells in Jupyter notebooks
• Added comprehensive test suite for the notebook operations

Changed

• Updated tools registration to include the new Jupyter notebook tools
• Enhanced README.md with Jupyter notebook functionality documentation

Added

• Added support for file paths in search_content and content_replace tools
• Extended functionality to search within and modify a single file directly
• Implemented smarter path handling to detect file vs directory inputs

Changed

• Updated docstrings to clarify that path parameter now accepts both file and directory paths
• Enhanced tool parameter descriptions for improved clarity

Improved

• Added extensive test coverage for the new file path functionality
• Improved error messaging for file operations

Added

• Enhanced directory_tree tool with depth limits and filtering capabilities
• Added parameter depth to control traversal depth (default: 3, 0 or -1 for unlimited)
• Added parameter include_filtered to optionally include commonly filtered directories
• Added statistics summary to directory tree output

Changed

• Improved directory tree output format from JSON to more readable indented text
• Added filtering for common development directories (.git, node_modules, etc.)
• Enhanced directory tree structure to show skipped directories with reason

Changed

• Improved README instructions regarding the placement of the system prompt in Claude Desktop
• Clarified that the system prompt must be placed in the "Project instructions" section for optimal performance

Changed

• Modified permissions system to allow access to .git folders by default
• Updated tests to reflect the new permission behavior