Add new observations, details, or information to existing entities in the user
AI agents use memory_add_observations to create or update resources in VaultAssist — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your VaultAssist environment.
This tool creates or modifies data in a reversible manner by appending observations to entities, which aligns with the Write category. It is not destructive (data is not deleted), not Execute (no arbitrary code or shell commands), and not Financial.
From the tool's definition The tool description states it will 'Add new observations, details, or information to existing entities in the user'. The verb 'Add' and action of appending information to entities indicates data modification.
Documented attack patterns abuse exactly the kind of access memory_add_observations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VaultAssist, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_add_observations:
{
"version": "1",
"default": "deny",
"tools": {
"memory_add_observations": {
"limits": [
{
"counter": "memory_add_observations_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}memory_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.
Add new observations, details, or information to existing entities in the user. It is categorised as a Write tool in the VaultAssist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the VaultAssist MCP server in PolicyLayer and add a rule for memory_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 VaultAssist. Nothing to install.
memory_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 memory_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 memory_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.
memory_add_observations is provided by the VaultAssist MCP server (3xcaffeine/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from VaultAssist, 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.
79 VaultAssist tools catalogued and risk-classified — across an index of 43,000+ MCP servers.