pause_instance
Temporarily stop one private instance WITHOUT unsubscribing: blocks new runs from starting, and asks any run in flight to stop. Everything is kept — the subscription, config, repos, documents, memory, timeline and run history — and resume_instance puts it straight back. This is the reversible alt...
This record as markdown: /tools/io-github-proagentstore-platform/pause-instance.md
What pause_instance does on ProAgentStore
AI agents invoke pause_instance 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 pause_instance is rated High
Pauses a running instance, affecting operational workflows and potentially disrupting active processes managed by external agents.
From the tool's definition Temporarily stop one private instance, blocks new runs, asks run in flight to stop
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs pause_instance 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 pause_instance, this is the rule to start with:
pause_instance 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 pause_instance call is checked against it from then on.
Questions about pause_instance
Temporarily stop one private instance WITHOUT unsubscribing: blocks new runs from starting, and asks any run in flight to stop. Everything is kept — the subscription, config, repos, documents, memory, timeline and run history — and resume_instance puts it straight back. This is the reversible alternative to cancel_instance, which gives the agent up. Background work is stopped too (cron triggers, the agent-to-agent pump, delivery retries, inbound webhooks). Chat still works, deliberately, so you can ask a paused agent what went wrong. 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 pause_instance: 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.
pause_instance 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 pause_instance 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 pause_instance. 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.
pause_instance 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