open_project · Scrivener MCP: Risk & Policy

WHAT IT DOES

What open_project does on Scrivener

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

WHY IT NEEDS A POLICY

Why open_project needs a policy

This tool changes the active project state on the server, which is a side-effectful write operation (modifying server-side state/session context). It does not merely read data — it sets a persistent active project context that affects all subsequent tool calls. It is not destructive, financial, or execute-level, but it does alter mutable state beyond a pure read.

From the tool's definition Opens a Scrivener project by name, making it the active project for all other tools.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

open_project Rate-limited

open_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": {
    "open_project": {
      "limits": [
        {
          "counter": "open_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 Scrivener, so you can run agents against it safely.

FAQ

Questions about open_project

What does the open_project tool do? +

Opens a Scrivener project by name, making it the active project for all other tools. It is categorised as a Write tool in the Scrivener MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on open_project? +

Register the Scrivener MCP server in PolicyLayer and add a rule for open_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 Scrivener. Nothing to install.

What risk level is open_project? +

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

Can I rate-limit open_project? +

Yes. Add a rate_limit block to the open_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 open_project completely? +

Set action: deny in the PolicyLayer policy for open_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 open_project? +

open_project is provided by the Scrivener MCP server (sschmitt-cg/scrivener-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.