Provide feedback to help Farnsworth improve. Positive or negative feedback helps the system learn and adapt.
AI agents use farnsworth_evolve 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 feedback data into the Farnsworth system to influence its learning and adaptation. It modifies the system's internal state/model by submitting positive or negative feedback. This is a Write operation (creating/modifying data) rather than Read, and while it affects system behavior, it is not irreversible deletion (Destructive) nor code execution (Execute).
From the tool's definition Provide feedback to help Farnsworth improve. Positive or negative feedback helps the system learn and adapt.
Documented attack patterns abuse exactly the kind of access farnsworth_evolve 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_evolve:
{
"version": "1",
"default": "deny",
"tools": {
"farnsworth_evolve": {
"limits": [
{
"counter": "farnsworth_evolve_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}farnsworth_evolve 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.
Provide feedback to help Farnsworth improve. Positive or negative feedback helps the system learn and adapt. 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_evolve: 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_evolve 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_evolve 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_evolve. 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_evolve 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.