config · Python MCP: Risk & Policy

WHAT IT DOES

What config does on Python

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

WHY IT NEEDS A POLICY

Why config needs a policy

This tool modifies git configuration settings through 'set' and 'unset' operations. While these changes are reversible (can be undone by setting different values), they still constitute Write operations that alter system/repository state. The tool also supports read-only actions ('get', 'list'), but the capability to modify configuration elevates it beyond Read.

From the tool's definition Tool description states 'Supports get, set, list, and unset actions.' The 'set' and 'unset' actions modify git configuration values, which are reversible changes to configuration state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

config Rate-limited

config 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": {
      "limits": [
        {
          "counter": "config_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 Python, so you can run agents against it safely.

FAQ

Questions about config

What does the config tool do? +

Manages git configuration values. Supports get, set, list, and unset actions. Operates at local, global, system, or worktree scope. It is categorised as a Write tool in the Python 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? +

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

What risk level is config? +

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

Can I rate-limit config? +

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

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

config is provided by the Python MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.