AI agents use farnsworth_remember to create or update resources in Farnsworth — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Farnsworth environment.
This tool writes/creates data by storing information in the persistent memory system. It has side effects (modifying memory state) but is not inherently destructive or financial. Misuse could lead to memory pollution or injection of false context that influences future agent behavior, hence medium severity.
From the tool's definition Store information in memory
Documented attack patterns abuse exactly the kind of access farnsworth_remember gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Farnsworth, and nothing reaches the server without passing your rules. This is the rule we recommend for farnsworth_remember:
{
"version": "1",
"default": "deny",
"tools": {
"farnsworth_remember": {
"limits": [
{
"counter": "farnsworth_remember_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}farnsworth_remember 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.
Store information in memory. It is categorised as a Write tool in the Farnsworth MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Farnsworth MCP server in PolicyLayer and add a rule for farnsworth_remember: 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 Farnsworth. Nothing to install.
farnsworth_remember 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 farnsworth_remember 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 farnsworth_remember. 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.
farnsworth_remember is provided by the Farnsworth MCP server (timowhite88/farnsworth). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 20 Farnsworth tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
20 Farnsworth tools catalogued and risk-classified — across an index of 42,500+ MCP servers.