// MCP TOOL REFERENCE

PYPI:MCP MEMORY TOOLS

14 tools from the Pypi:mcp Memory MCP Server, categorised by risk level.

View the Pypi:mcp Memory policy → Token cost: 1,161 tokens →

// ALL 14 PYPI:MCP MEMORY TOOLS

READ 6 tools

Read get_frequently_used Find entities that are accessed frequently Read get_stale_entities Find entities that haven't been updated recently Read read_graph Read the entire knowledge graph Read search_nodes Search for nodes in the knowledge graph based on a query Read validate_component_props Validate component props to prevent hallucination. Checks if props exist in @props observations Read verify_graph_integrity Verify the integrity of the knowledge graph by checking for orphaned entities in relationships. Returns hal...

WRITE 5 tools

Write add_observations Add new observations to existing entities in the knowledge graph Write create_entities Create multiple new entities in the knowledge graph Write create_relations Create multiple new relations between entities in the knowledge graph. Relations should be in active voice Write open_nodes Open specific nodes in the knowledge graph by their names Write update_entity Update an existing entity, preserving previous observations

DESTRUCTIVE 3 tools

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

// FAQ

How many tools does the Pypi:mcp Memory MCP server have? +

The Pypi:mcp Memory MCP server exposes 14 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Pypi:mcp Memory tools? +

Route the Pypi:mcp Memory server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Pypi:mcp Memory tools fall into? +

Pypi:mcp Memory tools are categorised as Read (6), Write (5), Destructive (3). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.