Ingest knowledge from URL into learning system
AI agents use learn_system_ingest to create or update resources in BWVI — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your BWVI environment.
This tool fetches content from a URL and writes/stores it into the learning system's knowledge base. It creates or modifies data within the system (adding new knowledge entries), which is a Write operation. It is reversible in principle (knowledge could be removed), so it doesn't qualify as Destructive.
From the tool's definition Ingest knowledge from URL into learning system
Documented attack patterns abuse exactly the kind of access learn_system_ingest gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and BWVI, and nothing reaches the server without passing your rules. This is the rule we recommend for learn_system_ingest:
{
"version": "1",
"default": "deny",
"tools": {
"learn_system_ingest": {
"limits": [
{
"counter": "learn_system_ingest_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}learn_system_ingest 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.
Ingest knowledge from URL into learning system. It is categorised as a Write tool in the BWVI MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the BWVI MCP server in PolicyLayer and add a rule for learn_system_ingest: 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 BWVI. Nothing to install.
learn_system_ingest 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 learn_system_ingest 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 learn_system_ingest. 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.
learn_system_ingest is provided by the BWVI MCP server (lh123aa/bwvi-design). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from BWVI, 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.
15 BWVI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.