Bootstrap memory from the current AI session. Returns extraction instructions — follow them to capture user context into Hippocampus.
AI agents use onboard to create or update resources in Hippocampus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hippocampus environment.
The tool creates and stores new memory records by extracting and persisting context from the current session. This is a reversible write operation (data can be updated or removed via sibling tools like 'forget' or 'update'), not destructive. While it doesn't directly execute code or commands, it does persistently modify the state of the knowledge graph storage.
From the tool's definition Tool description states it 'Bootstrap memory from the current AI session' and 'capture user context into Hippocampus', indicating creation/storage of new data in the memory system.
Documented attack patterns abuse exactly the kind of access onboard gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hippocampus, and nothing reaches the server without passing your rules. This is the rule we recommend for onboard:
{
"version": "1",
"default": "deny",
"tools": {
"onboard": {
"limits": [
{
"counter": "onboard_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}onboard 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.
Bootstrap memory from the current AI session. Returns extraction instructions — follow them to capture user context into Hippocampus. It is categorised as a Write tool in the Hippocampus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hippocampus MCP server in PolicyLayer and add a rule for onboard: 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 Hippocampus. Nothing to install.
onboard 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 onboard 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 onboard. 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.
onboard is provided by the Hippocampus MCP server (karrolcia/hippocampus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Hippocampus, 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 Hippocampus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.