The Grid Memory

neo4j-memory MCP

MCP server for the Grid's neo4j knowledge graph. 9 tools for entity creation, observations, relations, search, and full graph reads. Runs on Brain at port 8050. The Grid is ArcGrid's production knowledge graph — all facts about projects, people, and the platform live here.

MCPneo4jport 8050brain repoSSE transport

Overview

The neo4j-memory MCP server is the programmatic interface to the Grid's knowledge graph. All project facts, roadmap tasks, client records, people, decisions, and platform entity relations live in neo4j. Agents and Claude Code sessions interact with the graph exclusively through this MCP — never via direct Cypher connections.

This is distinct from atlas-memory MCP (port 8030), which handles per-session and per-user memory with ONNX embeddings. neo4j-memory is the canonical long-term knowledge graph.

Connection

# Claude Code MCP config (~/.claude/settings.json or project .mcp.json) { "mcpServers": { "neo4j-memory": { "url": "http://localhost:8050/mcp/" } } }

The server runs at http://localhost:8050/mcp/ on ArcHelm (Brain node). It is always running as part of the Brain cognitive stack in the agent-space-co/brain repo.

Tools (9)

create_entities(entities[])
Create one or more entities in the graph. Each entity has a name, type, and observations array.
add_observations(entityName, observations[])
Add observation strings to an existing entity.
create_relations(relations[])
Create directed relations between entities. Each relation has from, to, and relationType.
delete_entities(entityNames[])
Remove entities and all their relations from the graph.
delete_observations(entityName, observations[])
Remove specific observations from an entity.
delete_relations(relations[])
Remove specific relations from the graph.
find_memories_by_name(query)
Find entities by name (exact or fuzzy match).
read_graph()
Read the full graph — all entities, observations, and relations. Use sparingly; prefer search_memories.
search_memories(query)
Semantic search over the graph. Returns relevant entities and their observations.

Graph schema

Key entity types in the Grid graph:

  • RoadmapTask - linked to "Cost Optimization Roadmap" via PART_OF; sequential tasks linked via BLOCKS
  • Person - team members, clients, partners
  • Product - ArcGrid products and modules
  • Project - active client or internal projects
  • Decision - ratified architectural or product decisions
  • Integration - external services and how they connect

Naming conventions

All new facts — board names, group names, people, templates, URLs, IDs, project context — belong in neo4j, not in CLAUDE.md or system prompts. System prompts hold behavioral rules; the graph holds knowledge. When onboarding a new integration or agent, ask: "Is this a rule or a fact?" Rules go in prompts. Facts go in the graph.