skill_crud

A execute tool on the Skill Management MCP server.

SERVERSkill Management MCP Server SOURCEfkesheh/skill-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/fkesheh-skill-mcp/skill-crud.md

WHAT IT DOES

What skill_crud does on Skill Management MCP Server

AI agents invoke skill_crud to trigger actions in Skill Management 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.

RISK

Why skill_crud is rated High

CRUD operations on 'skills' in this context likely involve creating, reading, updating, and deleting skill definitions/scripts. The most severe applicable category across CRUD is Destructive (delete operations). However, since the description is empty and the tool name only says 'crud', there is uncertainty.

From the tool's definition Tool name 'skill_crud' on a server described as enabling Claude to 'create, edit, run, and manage reusable skills' with 'executing scripts with automatic dependency management'. Sibling tools include 'execute_python_code' and 'run_skill_script'.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs skill_crud safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Skill Management MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For skill_crud, this is the rule to start with:

skill_crud Rate-limited

skill_crud stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "skill_crud": {
      "limits": [
        {
          "counter": "skill_crud_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Skill Management MCP Server, apply this rule, and every skill_crud call is checked against it from then on.

FAQ

Questions about skill_crud

What does the skill_crud tool do? +

skill_crud is a execute tool on the Skill Management MCP Server MCP server. It is categorised as a Execute tool in the Skill Management MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on skill_crud? +

Register the Skill Management MCP Server MCP server in PolicyLayer and add a rule for skill_crud: 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 Skill Management MCP Server. Nothing to install.

What risk level is skill_crud? +

skill_crud is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit skill_crud? +

Yes. Add a rate_limit block to the skill_crud 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.

How do I block skill_crud completely? +

Set action: deny in the PolicyLayer policy for skill_crud. 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.

What MCP server provides skill_crud? +

skill_crud is provided by the Skill Management MCP Server MCP server (fkesheh/skill-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Skill Management MCP Server, and thousands of servers like it.

This server

All 5 Skill Management MCP Server tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →