Export conversation history, memories, and context to a shareable format (JSON, Markdown, HTML, or plain text). Use this to create backups or share your AI companion
AI agents call farnsworth_export to retrieve information from Farnsworth without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and serializes existing data (conversation history, memories, context) into an output format. It does not modify or delete data. However, it can expose potentially sensitive persistent memory and conversation history to external parties via export/sharing, giving it a medium severity despite being a read operation.
From the tool's definition Export conversation history, memories, and context to a shareable format (JSON, Markdown, HTML, or plain text). Use this to create backups or share your AI companion
Documented attack patterns abuse exactly the kind of access farnsworth_export 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_export:
{
"version": "1",
"default": "deny",
"tools": {
"farnsworth_export": {}
}
}farnsworth_export is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Export conversation history, memories, and context to a shareable format (JSON, Markdown, HTML, or plain text). Use this to create backups or share your AI companion. It is categorised as a Read tool in the Farnsworth MCP Server, which means it retrieves data without modifying state.
Register the Farnsworth MCP server in PolicyLayer and add a rule for farnsworth_export: 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_export is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the farnsworth_export 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_export. 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_export 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.