Memory Fts MCP server

claude-memory-fts

Long-term memory MCP server for Claude Code. Stores facts in a local SQLite database with hybrid search (FTS5 + semantic vector similarity) and automatic context injection.

Features

• Hybrid search — FTS5 keyword search + semantic vector similarity, merged via Reciprocal Rank Fusion (RRF)
• Semantic understanding — find memories by meaning, not just keywords (powered by all-MiniLM-L6-v2 embeddings)
• Auto context injection — top 30 most important memories injected into every prompt via hook
• Importance ranking — facts ranked by access frequency, recency decay, and category weight
• Access tracking — tracks how often each memory is accessed
• Upsert — automatically updates existing facts instead of duplicating
• Categorized — organize by type: preference, decision, technical, project, workflow, personal, general
• MCP Resources — exposes memory://context resource for session context
• Zero config — works out of the box, stores data in ~/.claude/memory.db

Install

# Add to Claude Code
claude mcp add memory -- npx claude-memory-fts

# Auto-configure context injection hook (recommended)
npx claude-memory-fts --setup-hook

The --setup-hook command automatically:

1. Creates ~/.claude/scripts/memory-context.sh
2. Adds a UserPromptSubmit hook to ~/.claude/settings.json
3. Top 30 memories are injected into every prompt automatically

CLI Commands

Configuration

Example with custom path:

claude mcp add memory -e MEMORY_DB_PATH=/path/to/my/memory.db -- npx claude-memory-fts

Tools

memory_save

Save a fact to long-term memory.

memory_search

Hybrid search: runs FTS5 and semantic search in parallel, merges results with RRF. Falls back to LIKE for partial matches.

memory_update

Update a memory's content or category by ID.

memory_list

List all saved memories grouped by category.

memory_delete

Delete a memory by ID.

Resources

memory://context

MCP resource exposing top 30 facts ranked by importance score:

• Access frequency — frequently accessed facts score higher (capped at 20 points)
• Recency — recently updated facts score higher (10 points, decays over 90 days)
• Category weight — preference/decision (3), workflow/technical (2), project/personal (1), general (0)

How It Works

Search Pipeline

Shortened. The full README is on GitHub.