config_write · Dobbe MCP: Risk & Policy

WHAT IT DOES

What config_write does on Dobbe

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

WHY IT NEEDS A POLICY

Why config_write needs a policy

This tool creates or modifies configuration data reversibly. It does not delete data (ruling out Destructive), execute arbitrary commands (ruling out Execute), or move money (ruling out Financial).

From the tool's definition Tool description explicitly states 'Set a configuration value' — a write operation that modifies persistent state in ~/.dobbe/config.toml.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

config_write Rate-limited

config_write 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": {
    "config_write": {
      "limits": [
        {
          "counter": "config_write_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Dobbe, so you can run agents against it safely.

FAQ

Questions about config_write

What does the config_write tool do? +

Set a configuration value in ~/.dobbe/config.toml. It is categorised as a Write tool in the Dobbe MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on config_write? +

Register the Dobbe MCP server in PolicyLayer and add a rule for config_write: 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 Dobbe. Nothing to install.

What risk level is config_write? +

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

Can I rate-limit config_write? +

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

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

config_write is provided by the Dobbe MCP server (nareshnavinash/dobbe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

config_write is one line of Dobbe's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →