// MCP TOOL REFERENCE

MEMORY TOOLS

9 tools from the Memory MCP Server, categorised by risk level.

READ TOOLS

read_graph Read the entire knowledge graph 2/5 search_nodes Search for nodes in the knowledge graph based on a query 2/5

WRITE TOOLS

add_observations Add new observations to existing entities in the knowledge graph 2/5 create_entities Create multiple new entities in the knowledge graph 2/5 create_relations Create multiple new relations between entities in the knowledge graph. Relations should be in active voice 2/5 open_nodes Open specific nodes in the knowledge graph by their names 2/5

DESTRUCTIVE TOOLS

delete_entities Delete multiple entities and their associated relations from the knowledge graph 4/5 delete_observations Delete specific observations from entities in the knowledge graph 4/5 delete_relations Delete multiple relations from the knowledge graph 4/5

// FAQ

How many tools does the Memory MCP server have? +

The Memory MCP server exposes 9 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Memory tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Memory server.

What risk categories do Memory tools fall into? +

Memory tools are categorised as Read (2), Write (4), Destructive (3). Each category has a recommended default policy.

Enforce policies on Memory

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →