save_project · Openl MCP: Risk & Policy

WHAT IT DOES

What save_project does on Openl

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

WHY IT NEEDS A POLICY

Why save_project needs a policy

This tool modifies data by saving changes to version control (Git commits). It creates new revisions and transitions project state, which are reversible write operations. While it commits changes, these are not destructive (can be reverted via Git) and don't execute arbitrary code or move financial resources.

From the tool's definition Saves project changes to Git. Works only when project status is EDITING (after opening and making changes). Requires comment (used as revision/commit message). Creates a new revision and transitions project to OPENED.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_project Rate-limited

save_project 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": {
    "save_project": {
      "limits": [
        {
          "counter": "save_project_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 Openl, so you can run agents against it safely.

FAQ

Questions about save_project

What does the save_project tool do? +

Save project changes to Git. Works only when project status is EDITING (after opening and making changes). Requires comment (used as revision/commit message). Creates a new revision and transitions project to OPENED. Optional closeAfterSave: true saves and closes in one request. Use after update_table, append_table, or other edits. Does not work for repository. It is categorised as a Write tool in the Openl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_project? +

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

What risk level is save_project? +

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

Can I rate-limit save_project? +

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

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

save_project is provided by the Openl MCP server (openl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.