Export memories as a CLAUDE.md context file, readable markdown, JSON, wire format, or Obsidian vault. Use claude-md for context files, markdown for human reading, json for backup/portability, wire for minimal tokens, obsidian for vault export with wikilinks.
AI agents call export to retrieve information from Hippocampus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and exports existing memory/knowledge graph data into various formats. It does not modify, delete, or create new data — it retrieves and serializes existing memories. However, it has medium severity because it can exfiltrate the entire knowledge graph (potentially sensitive persistent context) in bulk, making it a significant data exposure risk if misused by an AI agent.
From the tool's definition Export memories as a CLAUDE.md context file, readable markdown, JSON, wire format, or Obsidian vault
Documented attack patterns abuse exactly the kind of access export 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 export:
{
"version": "1",
"default": "deny",
"tools": {
"export": {}
}
}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 memories as a CLAUDE.md context file, readable markdown, JSON, wire format, or Obsidian vault. Use claude-md for context files, markdown for human reading, json for backup/portability, wire for minimal tokens, obsidian for vault export with wikilinks. It is categorised as a Read tool in the Hippocampus MCP Server, which means it retrieves data without modifying state.
Register the Hippocampus MCP server in PolicyLayer and add a rule for 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 Hippocampus. Nothing to install.
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 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 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.
export 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.