This record as markdown: /tools/hybridlabor-api-aos/manage-tools.md
What manage_tools does on Aos
AI agents invoke manage_tools to trigger actions in Aos. 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 manage_tools is rated High
This tool modifies the runtime configuration of the MCP server itself by enabling or disabling tools and categories. While it also has read aspects (list, view counts), the dominant and most severe capability is the ability to alter which tools are active at runtime, which is an operational execution-level action. Misuse could disable security-critical tools or enable dangerous ones, making severity high.
From the tool's definition 'enable/disable tools or categories at runtime' — dynamically alters which tools are available and active during execution
Attacks that exploit this kind of access
The rule that runs manage_tools safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Aos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For manage_tools, this is the rule to start with:
manage_tools 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 Aos, apply this rule, and every manage_tools call is checked against it from then on.
Questions about manage_tools
Dynamic MCP tool management. List canonical tools, view category counts, and enable/disable tools or categories at runtime. It is categorised as a Execute tool in the Aos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Aos MCP server in PolicyLayer and add a rule for manage_tools: 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 Aos. Nothing to install.
manage_tools 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 manage_tools 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 manage_tools. 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.
manage_tools is provided by the Aos MCP server (@hybridlabor-api/aos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Aos, and thousands of servers like it.
This server
Across the catalogue