Manage configured skill folders, blacklist, and reset to defaults. Mutates persisted config under defaultConfigPath().
AI agents use skills__configure to create or update resources in SkillForge MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SkillForge MCP environment.
This tool modifies persisted configuration (skill folders, blacklist settings) but does not delete data irreversibly or execute arbitrary code. Configuration changes are typically reversible (can be reconfigured or reset), placing it in the Write category.
From the tool's definition Description states "Mutates persisted config" and "Manage configured skill folders, blacklist, and reset to defaults" — these are reversible modifications to configuration state.
Attacks that exploit this kind of access
Manage configured skill folders, blacklist, and reset to defaults. Mutates persisted config under defaultConfigPath(). It is categorised as a Write tool in the SkillForge MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SkillForge MCP server in PolicyLayer and add a rule for skills__configure: 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 SkillForge MCP. Nothing to install.
skills__configure 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 skills__configure 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 skills__configure. 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.
skills__configure is provided by the SkillForge MCP server (lyupro/skillforge-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 →