Export conversation to JSON or Markdown format for backup or external use
AI agents use memory_export to create or update resources in Sekha MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sekha MCP Server environment.
The tool exports memory data to external formats, which modifies state by creating new artifacts (files or serialized outputs). This is a Write operation rather than Read because it generates and outputs data in a new form. It's not Destructive because the original data remains intact.
From the tool's definition Tool description states 'Export conversation to JSON or Markdown format for backup or external use' — this creates new files/outputs by serializing data, which is a write operation (data is materialized in a new format/location).
Attacks that exploit this kind of access
Export conversation to JSON or Markdown format for backup or external use. It is categorised as a Write tool in the Sekha MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sekha MCP Server MCP server in PolicyLayer and add a rule for memory_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 Sekha MCP Server. Nothing to install.
memory_export 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 memory_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 memory_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.
memory_export is provided by the Sekha MCP Server MCP server (sekha-ai/sekha-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →