Activate an installed skill.
AI agents invoke activate_skill to trigger actions in Friday MCP Server. 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.
Activating a skill causes installed code to run or become operational. Given the server supports 'self-extension via markdown-based skills' and has tools like install_skill_from_markdown/url, activating a skill is effectively enabling execution of arbitrary installed code. This falls under Execute since it triggers external operations whose effects depend on what the skill does.
From the tool's definition 'Activate an installed skill' — activating a skill triggers execution of previously installed code/functionality
Attacks that exploit this kind of access
Activate an installed skill. It is categorised as a Execute tool in the Friday MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Friday MCP Server MCP server in PolicyLayer and add a rule for activate_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 Friday MCP Server. Nothing to install.
activate_skill 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 activate_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 activate_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.
activate_skill is provided by the Friday MCP Server MCP server (jeremylakeyjr/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 →