(Revised Input) Add an episode to the Graphiti knowledge graph. Processes the episode addition asynchronously in the background. Episodes for the same group_id are processed sequentially. Args: name (str): Name of the episode episode_body (str): Supply the episode as one stringified JSON blob. • ...
AI agents use add_episode to create or update resources in Graphiti MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Graphiti MCP Server environment.
This tool creates new data (episodes) in the knowledge graph, which is a reversible modification. It accepts episode_body as input and stores it in Neo4j. While it modifies state, the action is not irreversible (episodes can be deleted via delete_episode tool), so it falls into Write rather than Destructive.
From the tool's definition Tool description explicitly states 'Add an episode to the Graphiti knowledge graph' and processes episode addition asynchronously, modifying the Neo4j knowledge graph with new data.
Documented attack patterns abuse exactly the kind of access add_episode gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Graphiti MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_episode:
{
"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.
Free to start. No card required.
(Revised Input) Add an episode to the Graphiti knowledge graph. Processes the episode addition asynchronously in the background. Episodes for the same group_id are processed sequentially. Args: name (str): Name of the episode episode_body (str): Supply the episode as one stringified JSON blob. • Triple‑escape all quotes so the inner JSON is valid inside the outer JSON args. • If format='json' → string must contain valid JSON. • If format='text' | 'message' → string is treated as raw text. group_id (str, optional): A unique ID for this graph. Defaults to config. format (str, optional): How to interpret the episode_body string ('text', 'json', 'message'). Defaults to 'text'. source_description (str, optional): Description of the source. uuid (str, optional): Optional UUID for the episode. entity_subset (list[str], optional): Optional list of entity names to use. It is categorised as a Write tool in the Graphiti MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Graphiti 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 MCP Server. Nothing to install.
add_episode is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
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.
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.
add_episode is provided by the Graphiti MCP Server MCP server (rawr-ai/mcp-graphiti). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Graphiti MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Graphiti MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.