config
Non-interactive config helpers (get/set/unset/file/validate). Default: starts guided setup.
This record as markdown: /tools/openclaw/config.md
What config does on OpenClaw
AI agents use config to create or update resources in OpenClaw, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OpenClaw environment.
Why config is rated Medium
The 'set' and 'unset' operations modify configuration data reversibly. While 'get' and 'validate' are read-only, the tool's primary capability includes state-changing writes. This is Write rather than Read because configuration changes can affect system behavior, authentication, permissions, and API credentials.
From the tool's definition Tool description explicitly mentions 'get/set/unset/file/validate' operations, with 'set' and 'unset' indicating modification of configuration state. 'file' suggests direct configuration file manipulation.
Attacks that exploit this kind of access
The rule that runs config safely
PolicyLayer is an MCP gateway: it sits between your AI agents and OpenClaw, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For config, this is the rule to start with:
config stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect OpenClaw, apply this rule, and every config call is checked against it from then on.
Questions about config
Non-interactive config helpers (get/set/unset/file/validate). Default: starts guided setup. It is categorised as a Write tool in the OpenClaw MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OpenClaw MCP server in PolicyLayer and add a rule for config: 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 OpenClaw. Nothing to install.
config 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 config 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 config. 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.
config is provided by the OpenClaw MCP server (openclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on OpenClaw, and thousands of servers like it.
This server
Across the catalogue