This record as markdown: /tools/abcxz-conviction-fm/toggle-agent.md
What toggle_agent does on Conviction
AI agents invoke toggle_agent to trigger actions in Conviction. 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 toggle_agent is rated High
Toggling an agent pauses or resumes its autonomous operation, including entering positions and capturing revenue from competition pools. While not directly moving money, it controls an agent that does, making it an Execute-level action with medium-to-high severity since misuse could halt a running strategy or resume a paused one unexpectedly.
From the tool's definition 'Pause or resume an agent' — triggers a state change in an external autonomous agent operating in a financial competition context
Attacks that exploit this kind of access
The rule that runs toggle_agent safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Conviction, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For toggle_agent, this is the rule to start with:
toggle_agent 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 Conviction, apply this rule, and every toggle_agent call is checked against it from then on.
Questions about toggle_agent
Pause or resume an agent. It is categorised as a Execute tool in the Conviction MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Conviction MCP server in PolicyLayer and add a rule for toggle_agent: 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 Conviction. Nothing to install.
toggle_agent 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 toggle_agent 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 toggle_agent. 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.
toggle_agent is provided by the Conviction MCP server (abcxz/conviction-fm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Conviction, and thousands of servers like it.
Across the catalogue