feat: add multi-project support to MCP tools

[PatD42]

Summary

• Add list_projects() and delete_project() methods to MemgraphIngestor class for project-scoped database operations
• Add 3 new MCP tools: list_projects, delete_project, wipe_database
• Modify index_repository to use project-scoped deletion instead of wiping entire database

This enables indexing multiple repositories without losing data from other projects when re-indexing a single repository.

Changes

graph_service.py

• list_projects(): Returns list of all indexed project names
• delete_project(project_name): Deletes all nodes with qualified_name starting with the project name prefix, preserving other projects

mcp/tools.py

• list_projects: MCP tool to list all indexed projects
• delete_project: MCP tool to delete a specific project
• wipe_database: MCP tool to clear entire database (requires confirmation flag)
• index_repository: Updated to use delete_project() instead of clean_database(), preserving other projects

Test plan

• Verify imports work correctly
• Run MCP tools integration tests (5/5 passed)
• Run type inference tests (2/2 passed)
• Manual testing with Memgraph to verify project isolation works

🤖 Generated with Claude Code

[gemini-code-assist]

Summary of Changes

Hello @PatD42, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the system's ability to manage knowledge graphs for multiple codebases. By introducing project-specific data handling and deletion mechanisms, it ensures that indexing or re-indexing one repository no longer impacts data from other projects, thereby improving data integrity and operational flexibility for users working with diverse codebases.

Highlights

• Multi-Project Support: Introduced methods and tools to manage multiple projects within the knowledge graph database, allowing for isolated data handling.
• Project-Scoped Deletion: Implemented functionality to delete data for a specific project without affecting other indexed projects.
• New MCP Tools: Added list_projects, delete_project, and wipe_database tools to provide granular control over indexed data within the Memgraph knowledge graph.
• Improved Indexing Workflow: Modified the index_repository tool to perform project-scoped re-indexing, preventing accidental data loss from other projects when re-indexing a single repository.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces multi-project support by adding tools to list and delete projects, and updating the repository indexing logic to be project-scoped. The changes are well-implemented, adding list_projects, delete_project, and wipe_database tools and their corresponding service methods. The index_repository tool is correctly modified to use delete_project, preventing data loss from other projects during re-indexing. I have one suggestion to improve the efficiency and atomicity of the project deletion logic in graph_service.py by combining two separate database queries into a single one.

[PatD42]

Addressing Gemini's atomicity concern:

Simplified delete_project() to use a single atomic query instead of count + delete:

# Before (2 queries, not atomic):
count_result = self.fetch_all("MATCH (n) ... RETURN count(n)")
self._execute_query("MATCH (n) ... DETACH DELETE n")
return node_count

# After (1 query, atomic):
self._execute_query("MATCH (n) ... DETACH DELETE n")

Why not use Gemini's suggestion?

Gemini proposed WITH n DETACH DELETE n RETURN count(n), but RETURN count(n) after DETACH DELETE n may not work correctly since the nodes are deleted before the count.

The simpler solution: just drop the count. It was only used for logging/cosmetic purposes and isn't essential for correctness.