Disable KAIROS on a session.
AI agents use kairos_disable to create or update resources in OpenClaude MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenClaude MCP Server environment.
Disabling KAIROS modifies the configuration/state of a session by turning off a feature. Since the sibling tool 'kairos_enable' exists to reverse this action, the operation is reversible and falls under Write rather than Destructive.
From the tool's definition 'Disable KAIROS on a session' — deactivates a feature/mode on an existing session, which is a reversible state change (can be re-enabled via kairos_enable sibling tool).
Attacks that exploit this kind of access
Disable KAIROS on a session. It is categorised as a Write tool in the OpenClaude MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenClaude MCP Server MCP server in PolicyLayer and add a rule for kairos_disable: 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 OpenClaude MCP Server. Nothing to install.
kairos_disable 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 kairos_disable 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 kairos_disable. 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.
kairos_disable is provided by the OpenClaude MCP Server MCP server (sandraschi/openclaude-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 →