Skip to main content
Glama
harbz07

Hippocampal Memory MCP

by harbz07

🧠 Hippocampal Memory MCP Server

An MCP server for neuroanatomically-inspired memory consolidation using Neo4j and semantic search.

Features

  • Episodic Memory Encoding: Create memory events with emotional valence and temporal context

  • Semantic Retrieval: Vector similarity search using OpenAI embeddings

  • Graph Operations: Full Cypher query support for reading and writing

  • Relationship Tracking: Monitor bond strength evolution over time

  • Extensible Schema: Additional tools in hippocampus-extension.mjs ready for integration

Related MCP server: RAG Memory MCP

Quick Start

See CHECKLIST.md for daily startup instructions.

1. Install Dependencies

npm install

2. Setup Neo4j

You need Neo4j Desktop running locally with a database on port 7687.

3. Initialize Schema

npm run setup-schema

4. Setup Tunnel (for remote access)

Start ngrok to expose your local Neo4j:

ngrok tcp 7687

Copy the tunnel URL (e.g., tcp://2.tcp.us-cal-1.ngrok.io:12841)

5. Configure Claude Desktop

Edit %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "hippocampal-memory": {
      "command": "node",
      "args": ["C:\\Users\\harve\\Neo4j\\hippocampal-mcp-server.mjs"],
      "env": {
        "NEO4J_URI": "bolt://YOUR_NGROK_URL",
        "NEO4J_USER": "neo4j",
        "NEO4J_PASSWORD": "your_password",
        "OPENAI_API_KEY": "your_openai_key"
      }
    }
  }
}

6. Start Claude Desktop

The MCP server will connect automatically.

Available Tools (8)

Hippocampus Module (Biomimetic Schema)

  1. hippocampus_write_event - Structured event creation with Who/Why/What/Where/Effects blocks

  2. hippocampus_write_reflection - Agent-relative memory slices with egocentric perspective

  3. hippocampus_search_events - Pattern completion retrieval with temporal/participant/effect filters

Core Memory Tools

  1. encode_memory - Save episodic memories with vector embeddings

  2. recall_memory - Semantic + temporal + emotional search

  3. query_graph - Read-only Cypher queries

  4. mutate_graph - Write operations (CREATE, MERGE, etc.)

  5. evolve_bond - Track relationship dynamics over time

Architecture

Current Setup:

Files:

Schema

Core Nodes:

  • Event - Episodic memories with vector embeddings

  • Person - Human and AI entities

  • Project - Ongoing work

  • Concept - Abstract ideas

  • Place, Catalyst, Entity, Target, Effect, Reflection, Agent (extension schema)

Key Relationships:

  • INVOLVES - Event → Entity (with role & salience)

  • PRECEDED - Event → Event (causal chains)

  • CONSOLIDATED_TO - Event → Concept/Person/Project

  • BOND - Person ↔ Person (with strength trajectory)

  • PARTICIPATED_IN, CATALYZED_BY, HELD_AT, HAD_EFFECT_ON, etc. (extension schema)

Indexes:

  • Vector index on Event.embedding (1536 dimensions, cosine similarity)

  • Unique constraints on id fields for Person, Project, Concept, Event

Important Notes

  • ngrok URL changes on every restart (unless you pay for static URL)

  • Update NEO4J_URI in Claude Desktop config when ngrok URL changes

  • Neo4j Desktop must be running before starting Claude Desktop

  • Environment variables are in Claude Desktop config (NOT .env file)

  • Render deployment requires persistent Neo4j (Aura) - local tunnel won't work

Testing

Test local connection:

node test-connection.mjs

Test tunnel connection:

node test-tunnel.mjs

Documentation

Deployment

Currently deployed to Render at: https://hippocampal-memory-mcp.onrender.com

For deployment details, see archived docs.

F
license - not found
-
quality - not tested
D
maintenance

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/harbz07/hippocampal-memory-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server