// SCAN REPORT

Graphiti MCP Demo

8 tools. 4 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 11 Jun 2026

4 can modify or destroy data

4 read-only

8 tools total

Community server · catalogue entry verified 11/06/2026

How to control Graphiti MCP Demo ↓

TOOL MAP

What Graphiti MCP Demo exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Graphiti MCP Demo tools

Destructive · High clear_graph This tool performs irreversible deletion of entire datasets (all graph memory), which cannot be undone without restore from backup. Destructive · High delete_entity_edge This tool performs an irreversible deletion operation on persisted graph data. Destructive · High delete_episode This tool permanently removes episode data from the knowledge graph, an operation that cannot be undone. Write · Medium add_memory The tool name 'add_memory' clearly indicates creation or modification of data within the knowledge graph.

4 of Graphiti MCP Demo's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Graphiti MCP Demo

PolicyLayer is an MCP gateway — it sits between your AI agents and Graphiti MCP Demo, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clear_graph": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "add_memory": {
    "limits": [
      {
        "counter": "add_memory_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_entity_edge": {
    "limits": [
      {
        "counter": "get_entity_edge_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Graphiti MCP Demo — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON GRAPHITI MCP DEMO →

Free to start. No card required.

FULL CATALOGUE

All 8 Graphiti MCP Demo tools

DESTRUCTIVE 3 tools

Destructive clear_graph Clear all data from the graph memory and rebuild indices. Destructive delete_entity_edge Delete an entity edge from the graph memory. Destructive delete_episode Delete an episode from the graph memory.

WRITE 1 tools

Write add_memory add_memory

READ 4 tools

Read get_entity_edge Get an entity edge from the graph memory by its UUID. Read get_episodes Get the most recent memory episodes for a specific group. Read search_memory_facts Search the graph memory for relevant facts. Read search_memory_nodes search_memory_nodes

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Graphiti MCP Demo

Can an AI agent delete data through the Graphiti MCP Demo MCP server? +

Yes. The Graphiti MCP Demo server exposes 3 destructive tools including clear_graph, delete_entity_edge, delete_episode. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Graphiti MCP Demo? +

The Graphiti MCP Demo server has 1 write tools including add_memory. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Graphiti MCP Demo.

How many tools does the Graphiti MCP Demo MCP server expose? +

8 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Graphiti MCP Demo? +

Register the Graphiti MCP Demo MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Graphiti MCP Demo tool call.

Deterministic rules across all 8 Graphiti MCP Demo tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON GRAPHITI MCP DEMO →

Free to start. No card required.

8 Graphiti MCP Demo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.