garden_plant · Synapse MCP: Risk & Policy

WHAT IT DOES

What garden_plant does on Synapse

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

WHY IT NEEDS A POLICY

Why garden_plant needs a policy

garden_plant creates or modifies data in the Obsidian vault by saving notes and synthesized information. This is reversible (notes can be edited or deleted later), placing it in the Write category rather than Destructive. Severity is medium because unauthorized writes to a personal knowledge base could pollute or corrupt the user's information store, but the blast radius is limited to that individual's vault.

From the tool's definition Tool description states 'Save proactively after decisions, research synthesis, templates, lessons, or completed work' — the verb 'Save' indicates creation or modification of data in the Obsidian vault.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

garden_plant Rate-limited

garden_plant 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": {
    "garden_plant": {
      "limits": [
        {
          "counter": "garden_plant_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 Synapse, so you can run agents against it safely.

FAQ

Questions about garden_plant

What does the garden_plant tool do? +

Save proactively after decisions, research synthesis, templates, lessons, or completed work — don. It is categorised as a Write tool in the Synapse MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on garden_plant? +

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

What risk level is garden_plant? +

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

Can I rate-limit garden_plant? +

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

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

garden_plant is provided by the Synapse MCP server (tomjrworks/synapse-obsidian). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.