Claude Session Memory Indexer

Claude Session Memory Indexer MCP Connector for Claude

A+

Preserves and retrieves cross-session learnings using deterministic hashing and Jaccard similarity.

3 tools Official Updated Oct 1, 2026 Official Vinkius Partner

This MCP server solves the problem of lost context in AI coding sessions. It indexes and retrieves cross-session learnings by mapping developer insights to specific project contexts using deterministic hashing. By using get_project_context, the system ensures that insights are isolated to the correct project. You can use index_learning to save new patterns or commands, and query_memories to retrieve them using keyword matching and Jaccard similarity. This allows your AI assistant to remember build commands, debugging patterns, and project conventions across different sessions.

memoryindexingcontextclaudeknowledge-management

3 tools expose this connector's capabilities to your AI agent.

get_project_context

Provides the current project's unique identity to the caller

index_learning

Persists a new insight or learning into the long-term memory store

query_memories

Searches for relevant past learnings based on a user's current context or question

See how to talk to your AI agent using Claude Session Memory Indexer.

How do I run the build for this project?

To run the build, use the command `npm run build` as specified in your project's build commands.

What are the project conventions for naming files?

The project follows kebab-case for all file names.

I'm seeing a recurring error with the database connection. Have we seen this before?

Yes, a similar issue was recorded. It usually occurs when the environment variable `DB_URL` is missing from the local configuration.

The system uses a unique project hash generated from your `CLAUDE.md` and directory structure. This ensures that `index_learning` only stores and retrieves memories belonging to the specific project context.

Related Connectors