session_export
Export an AI agent session as a portable bundle. The bundle contains conversation history, agent-specific session files, and optionally workspace info (git patch or tar). Use this to prepare a session for transfer to another machine.
This record as markdown: /tools/io-github-kivanccakmak-yaver/session-export.md
What session_export does on Yaver
AI agents call session_export to retrieve information from Yaver without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
task_id | string | Yes | The task ID of the session to export |
workspace_mode | string | — | How to include workspace: 'none', 'git' (git patch), or 'tar'. Default: 'git' if git repo, else 'none'. |
include_workspace | boolean | — | Include workspace files in the bundle (default: false) |
Parameters from the server's own tool schema.
Why session_export is rated Low
The tool reads and packages existing session data (conversation history, session files, workspace info) into a bundle for transfer. It does not modify or delete data. However, it can include workspace contents (git patch or tar), which means it could exfiltrate sensitive code or data if misused, warranting a medium severity despite being a read operation.
From the tool's definition Export an AI agent session as a portable bundle. The bundle contains conversation history, agent-specific session files, and optionally workspace info (git patch or tar).
Attacks that exploit this kind of access
The rule that runs session_export safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For session_export, this is the rule to start with:
session_export is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every session_export call is checked against it from then on.
Questions about session_export
Export an AI agent session as a portable bundle. The bundle contains conversation history, agent-specific session files, and optionally workspace info (git patch or tar). Use this to prepare a session for transfer to another machine. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
session_export accepts 3 parameters: task_id, workspace_mode, include_workspace. Required: task_id. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for session_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 Yaver. Nothing to install.
session_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 session_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 session_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.
session_export is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue