Returns the content of multiple best practice skills
AI agents call get_skills to retrieve information from Personal Code Skills MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns existing markdown documentation about coding best practices. No side effects occur; it does not create, modify, delete, or execute anything. The plural 'get_skills' suggests it retrieves multiple skill documents, similar to its sibling 'get_skill', making it a straightforward Read operation with minimal risk if misused by an AI agent.
From the tool's definition Tool returns content of best practice skills files - a retrieval operation with no modification capability.
Attacks that exploit this kind of access
Returns the content of multiple best practice skills. It is categorised as a Read tool in the Personal Code Skills MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Personal Code Skills MCP Server MCP server in PolicyLayer and add a rule for get_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 Personal Code Skills MCP Server. Nothing to install.
get_skills is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_skills is provided by the Personal Code Skills MCP Server MCP server (lfdantoni/my-personal-code-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 →