Medium Risk

add_episode

Add an episode to the knowledge graph (supports text, JSON, and message formats)

How to control add_episode ↓

What add_episode does on Graphiti Knowledge Graph MCP Server

AI agents use add_episode to create or update resources in Graphiti Knowledge Graph MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Graphiti Knowledge Graph MCP Server environment.

Medium Risk

Why add_episode needs a policy

The tool creates and inserts new episode records into a persistent knowledge graph structure. This is a reversible Write operation—data can be added but is not destructive. While sibling tools like delete_episode and clear_graph could modify or remove data, add_episode itself only creates new entries.

From the tool's definition Tool name 'add_episode' and description 'Add an episode to the knowledge graph' indicates creation of new data within the knowledge graph system.

Documented attack patterns abuse exactly the kind of access add_episode gives an agent:

How to control add_episode

PolicyLayer is an MCP gateway — it sits between your AI agents and Graphiti Knowledge Graph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_episode:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_episode": {
      "limits": [
        {
          "counter": "add_episode_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

add_episode stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Graphiti Knowledge Graph MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about add_episode

What does the add_episode tool do? +

Add an episode to the knowledge graph (supports text, JSON, and message formats). It is categorised as a Write tool in the Graphiti Knowledge Graph MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_episode? +

Register the Graphiti Knowledge Graph MCP Server MCP server in PolicyLayer and add a rule for add_episode: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Graphiti Knowledge Graph MCP Server. Nothing to install.

What risk level is add_episode? +

add_episode is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_episode? +

Yes. Add a rate_limit block to the add_episode rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block add_episode completely? +

Set action: deny in the PolicyLayer policy for add_episode. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides add_episode? +

add_episode is provided by the Graphiti Knowledge Graph MCP Server MCP server (michabbb/graphiti-mcp-but-working). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Graphiti Knowledge Graph MCP Server tool call.

Start from Graphiti Knowledge Graph MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

11 Graphiti Knowledge Graph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.