Update a skill
AI agents use maasy_update_skill to create or update resources in Maasy — AI Marketing Copilot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Maasy — AI Marketing Copilot environment.
This tool modifies skill definitions within the marketing copilot system. Updates are generally reversible (can be updated again), placing it in the Write category rather than Destructive. Severity is medium because incorrect skill updates could affect marketing campaign behavior and customer interactions, but the impact is typically scoped to that skill's scope and reversible.
From the tool's definition Tool name 'maasy_update_skill' combined with description 'Update a skill' indicates modification of existing data.
Attacks that exploit this kind of access
Update a skill. It is categorised as a Write tool in the Maasy — AI Marketing Copilot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Maasy — AI Marketing Copilot MCP server in PolicyLayer and add a rule for maasy_update_skill: 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 Maasy — AI Marketing Copilot. Nothing to install.
maasy_update_skill 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 maasy_update_skill 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 maasy_update_skill. 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.
maasy_update_skill is provided by the Maasy — AI Marketing Copilot MCP server (@maasy-ai/mcp-server). 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 →