Qualitative Researcher MCP Server

A precise tool for removing elements from the qualitative research knowledge graph, enabling researchers to maintain data accuracy and refine their analytical framework. When to use this tool: - Removing incorrect or duplicate research entities - Deleting erroneous relationships between research elements - Clearing outdated observations from research entities - Restructuring your research framework as analysis evolves - Removing pilot or test data that shouldn't be included in final analysis - Cleaning up the knowledge graph during research refinement phases - Eliminating deprecated codes, themes, or concepts that no longer fit your analytical framework - Removing sensitive information that should not be retained - Reorganizing your analytical structure by removing and recreating elements - Updating status assignments when research activities change state - Modifying priority assignments as research focus shifts - Restructuring sequential relationships between research processes Key features: - Provides targeted deletion capabilities for three distinct types of knowledge graph elements: entities, relations, and observations - Maintains knowledge graph integrity during deletion operations - Supports batch deletion of multiple items in a single operation - Returns clear confirmation of deletion results - Preserves the overall structure of the research knowledge graph while removing specific elements - Performs validation to ensure deletion requests are properly formatted - Handles status and priority relation management - Supports modification of sequential process relationships Parameters explained: 1. type: The type of deletion operation to perform - Accepts: "entities", "relations", or "observations" - Determines how the data parameter is interpreted 2. data: The elements to remove from the knowledge graph (structure varies by type): - For "entities": Array of entity names to delete * Example: ["Participant_A", "Interview_3"] - For "relations": Array of relation objects, each containing: * from: Name of the source entity * to: Name of the target entity * relationType: Type of relationship to remove (e.g., "participated_in", "codes", "has_status", "has_priority", "precedes") - For "observations": Array of objects, each containing: * entityName: Name of the entity to remove observations from * indices: Array of numeric indices identifying which observations to remove Deletion behavior by type: - Entities: Removes the specified entities and all their associated relations from the knowledge graph - Relations: Removes only the specified relationships, leaving the connected entities intact - Observations: Removes specific observations from entities while preserving the entities themselves Status and Priority Management: - When deleting status or priority entities, be aware of the impact on entities that reference them - For changing an entity's status or priority, first delete the existing has_status or has_priority relation, then create a new one - Consider the research workflow implications when removing status entities or relations - Deletion of a status entity will remove all has_status relations pointing to it Sequential Process Management: - Removing precedes relations affects the logical flow of research processes - Consider restructuring sequential relationships after deletion to maintain process continuity - When reorganizing research phases, update all affected precedes relations Safety considerations: - Entity deletion is permanent and will also remove all relationships involving those entities - Consider exporting or backing up your research knowledge graph before performing large-scale deletions - For sensitive operations, consider removing specific observations rather than entire entities - When removing codes or themes, consider the impact on your analytical framework - Status changes should be carefully managed to maintain accurate research progress tracking - Changes to sequential relationships may affect dependent research activities Return information: - JSON response indicating success or failure - For successful operations: * Success flag set to true * Confirmation message - For failed operations: * Success flag set to false * Error message describing the issue You should: - Be specific in your deletion requests to avoid unintended data loss - Use relations deletion when you want to disconnect entities without removing them - For observations, provide the exact indices to ensure only the intended content is removed - When restructuring your analysis, consider how deletions will affect related elements - Use deletecontext in conjunction with buildcontext to refine and evolve your research framework - Regularly review your knowledge graph for elements that may need to be removed or updated - Consider the cascading effects of entity deletion on your overall research structure - Use observation deletion for minor corrections rather than removing entire entities - When updating entity status, delete the old has_status relation before creating a new one - Maintain logical consistency when modifying sequential process relationships