MCP server added #22
Open
MCP server added #22
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Create mcp_treequest package with complete MCP server - Implement session management for stateful tree search operations - Add tools for init_tree, step_tree, get_tree_state, rank_nodes, list_sessions, delete_session - Support all TreeQuest algorithms: StandardMCTS, ABMCTSA, ABMCTSM - Add MCP dependencies and CLI entry point to pyproject.toml - Support both stdio and SSE transport modes Implements GitHub issue SakanaAI#7: SakanaAI#7 Co-Authored-By: Erkin Alp Güney <[email protected]>
- Update CLI script entry point to use server:main directly - Add comprehensive README.md with usage examples and tool documentation - Document both stdio and SSE transport modes Co-Authored-By: Erkin Alp Güney <[email protected]>
- Implement get_tree_visualization tool with Graphviz integration - Support multiple output formats (png, pdf, svg, dot) - Add configurable parameters for scores, labels, and titles - Include comprehensive error handling for missing dependencies - Complete utility tools implementation for MCP server Co-Authored-By: Erkin Alp Güney <[email protected]>
- Add _validate_session_exists() for session ID validation - Add _validate_algorithm_params() for parameter range validation - Add _validate_generate_functions() with security checks - Enhance init_tree_tool with parameter validation and specific error types - Enhance step_tree_tool with session validation, syntax error handling, and security - Enhance rank_nodes_tool with k parameter validation and tree state checks - Provide clear, actionable error messages for all validation failures - Add limits and safety checks for user inputs Co-Authored-By: Erkin Alp Güney <[email protected]>
- Add get_tree_visualization tool documentation with all parameters - Include advanced generate function examples for math, text, and game scenarios - Add comprehensive error handling and troubleshooting sections - Include integration guides for Claude Desktop and MCP CLI tools - Add algorithm comparison table and performance optimization tips - Provide detailed workflow examples with realistic use cases Co-Authored-By: Erkin Alp Güney <[email protected]>
- Fix Bug 1: Pass state instead of tree to top_k function - Fix Bug 2: Filter algorithm parameters by algorithm type to prevent invalid params - Fix Flag 1: Add asyncio.Lock for thread-safe session dictionary access - Fix Flag 2: Replace simple substring matching with AST-based security validation - Fix Flag 3: Use consistent _validate_session_exists() across all tools Co-Authored-By: Erkin Alp Güney <[email protected]>
Complete MCP server implementation with session management Support for all TreeQuest algorithms with configurable parameters Tools for tree initialization, stepping, state retrieval, node ranking, and visualization Both stdio and SSE transport modes Comprehensive error handling and input validation CLI entry point and proper package configuration Extensive documentation with usage examples
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.