AI agents use n2n_add_observations to create or update resources in N2n Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your N2n Memory environment.
This tool creates or adds observations to a knowledge graph stored in a project directory. While the description is empty, the name and server context show it modifies persisted data reversibly (observations can be deleted via n2n_delete_observations). This is a Write operation.
From the tool's definition Tool name 'n2n_add_observations' and sibling tools 'n2n_delete_observations', 'n2n_create_relations', 'n2n_delete_entities' indicate a knowledge graph modification system.
Documented attack patterns abuse exactly the kind of access n2n_add_observations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and N2n Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for n2n_add_observations:
{
"version": "1",
"default": "deny",
"tools": {
"n2n_add_observations": {
"limits": [
{
"counter": "n2n_add_observations_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}n2n_add_observations 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.
n2n_add_observations. It is categorised as a Write tool in the N2n Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the N2n Memory MCP server in PolicyLayer and add a rule for n2n_add_observations: 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 N2n Memory. Nothing to install.
n2n_add_observations 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 n2n_add_observations 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 n2n_add_observations. 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.
n2n_add_observations is provided by the N2n Memory MCP server (n2ns/n2n-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from N2n Memory, 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.
12 N2n Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.