emx-mcp-server

CoderDayton/emx-mcp-server

3.2

If you are the rightful owner of emx-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

EMX-MCP Server is a Python library designed to provide comprehensive support for infinite-context episodic memory for AI agents, implementing the EM-LLM algorithm using embedding-based approaches.

Tools

Functions exposed to the LLM to take actions

store_memory

Store conversations/documents with automatic segmentation and boundary refinement.

recall_memories

Semantic search across project/global memory with concise or detailed results.

remove_memories

Selectively delete specific memories by event IDs.

search_memory_batch

High-throughput batch retrieval with adaptive CPU/GPU routing.

manage_memory

Administrative operations: stats, retrain, optimize, clear, estimate.

transfer_memory

Import/export memory archives with optimal nlist hints.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources