agentbrush_init

SERVERMcp Server SOURCE@agentbrush/mcp-server

Medium RISK CLASS

Category Write

Parameters 20 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/dev-agentbrush-mcp-server/agentbrush-init.md

WHAT IT DOES

What agentbrush_init does on Mcp Server

AI agents use agentbrush_init to create or update resources in Mcp Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Server environment.

Parameter	Type	Required	Description
`cli_tool`	string	—	Coding agent being set up. Used by the CLI to tailor next-step guidance.
`project_dir`	string	—	Project root directory. Defaults to current working directory.

Parameters from the server's own tool schema.

RISK

Why agentbrush_init is rated Medium

This tool creates new files and directories in the project (Write category). It explicitly states it is non-destructive and skips existing files, so no data is overwritten or deleted. The blast radius is low since it only scaffolds a local project directory structure with no authentication or external operations.

From the tool's definition Creates .agentbrush/ directory with identity.json and references/ folder. Non-destructive: skips files that already exist.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs agentbrush_init safely

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

agentbrush_init Rate-limited

agentbrush_init stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "agentbrush_init": {
      "limits": [
        {
          "counter": "agentbrush_init_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about agentbrush_init

What does the agentbrush_init tool do? +

Initialize AgentBrush in a project. Creates .agentbrush/ directory with: - identity.json: brand identity stub (style descriptor, color palette, mood tags) - references/: folder for reference images Non-destructive: skips files that already exist. Call this once per project before using brand identity features. This scaffolds project files only; it does not authenticate. Use the agentbrush_login tool (or run agentbrush-mcp init in a terminal) to connect an account. It is categorised as a Write tool in the Mcp Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does agentbrush_init accept? +

agentbrush_init accepts 2 parameters: cli_tool, project_dir. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on agentbrush_init? +

Register the Mcp Server MCP server in PolicyLayer and add a rule for agentbrush_init: 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 Mcp Server. Nothing to install.

What risk level is agentbrush_init? +

agentbrush_init is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit agentbrush_init? +

Yes. Add a rate_limit block to the agentbrush_init 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 agentbrush_init completely? +

Set action: deny in the PolicyLayer policy for agentbrush_init. 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 agentbrush_init? +

agentbrush_init is provided by the Mcp Server MCP server (@agentbrush/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Server, and thousands of servers like it.

This server

All 12 Mcp Server tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →