AI agents use register-skills to create or update resources in Mmc — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mmc environment.
This tool creates or modifies session-scoped skill definitions. It is Write rather than Execute because it does not directly run code or trigger external operations; it stores/registers configuration. It is not Destructive because registration is reversible (a new session or re-registration can override it).
From the tool's definition Tool description states "Register skill/slice definitions for this session" — this is a create/write operation that establishes new skill definitions. The name "register-skills" also indicates a registration (creation) action rather than retrieval or deletion.
Attacks that exploit this kind of access
Register skill/slice definitions for this session. Skills are session-scoped and isolated from other users. Typically called by the workbench test panel to push the current model. It is categorised as a Write tool in the Mmc MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mmc MCP server in PolicyLayer and add a rule for register-skills: 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 Mmc. Nothing to install.
register-skills 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 register-skills 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 register-skills. 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.
register-skills is provided by the Mmc MCP server (modelmycontext/mmc-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 →