end_instance_takeover
End a human-takeover session, handing the browser back. This does NOT resume the run — use resume_instance_takeover for that. Ending is the one takeover control whose failure is invisible from outside: if it fails the agent still holds the browser and the run is still blocked, so check the result...
This record as markdown: /tools/io-github-proagentstore-platform/end-instance-takeover.md
What end_instance_takeover does on ProAgentStore
AI agents invoke end_instance_takeover to trigger actions in ProAgentStore. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why end_instance_takeover is rated High
Terminates active browser control session; agent regains control, unblocking paused execution.
From the tool's definition End human-takeover session, handing browser back, unresumes run.
Attacks that exploit this kind of access
The rule that runs end_instance_takeover safely
PolicyLayer is an MCP gateway: it sits between your AI agents and ProAgentStore, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For end_instance_takeover, this is the rule to start with:
end_instance_takeover stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect ProAgentStore, apply this rule, and every end_instance_takeover call is checked against it from then on.
Questions about end_instance_takeover
End a human-takeover session, handing the browser back. This does NOT resume the run — use resume_instance_takeover for that. Ending is the one takeover control whose failure is invisible from outside: if it fails the agent still holds the browser and the run is still blocked, so check the result rather than assuming. It is categorised as a Execute tool in the ProAgentStore MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ProAgentStore MCP server in PolicyLayer and add a rule for end_instance_takeover: 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 ProAgentStore. Nothing to install.
end_instance_takeover is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the end_instance_takeover 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 end_instance_takeover. 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.
end_instance_takeover is provided by the ProAgentStore MCP server (https://mcp.proagentstore.online/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on ProAgentStore, and thousands of servers like it.
Across the catalogue