pull_repo · Databricks MCP Server MCP: Risk & Policy

WHAT IT DOES

What pull_repo does on Databricks MCP Server

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

WHY IT NEEDS A POLICY

Why pull_repo needs a policy

Pulling a repo updates the local workspace copy to match the remote repository's latest commit. This modifies the existing repo contents in the Databricks workspace (overwriting local changes), making it a Write operation. It could overwrite uncommitted local changes, but is generally reversible by checking out a previous commit. It does not execute code or delete data irreversibly.

From the tool's definition Pull the latest commit for a repo

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pull_repo Rate-limited

pull_repo 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": {
    "pull_repo": {
      "limits": [
        {
          "counter": "pull_repo_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 Databricks MCP Server, so you can run agents against it safely.

FAQ

Questions about pull_repo

What does the pull_repo tool do? +

Pull the latest commit for a repo with parameter: repo_id (required). It is categorised as a Write tool in the Databricks MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on pull_repo? +

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

What risk level is pull_repo? +

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

Can I rate-limit pull_repo? +

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

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

pull_repo is provided by the Databricks MCP Server MCP server (robkisk/databricks-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.