AI agents call garden_read to retrieve information from Synapse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from an Obsidian vault with no side effects. It performs a read operation on existing notes without creating, modifying, deleting, or executing any code. The low severity reflects that unauthorized access to personal notes, while a privacy concern, does not enable destructive or financial harm compared to other categories.
From the tool's definition Tool name is 'garden_read' and description explicitly states it is used 'whenever the user wants to read, open, or fetch the full content of a known note path.' The tool 'Returns the full file including frontmatter' with no mention of modification, deletion,…
Attacks that exploit this kind of access
Use this whenever the user wants to read, open, or fetch the full content of a known note path. Returns the full file including frontmatter. Triggers:. It is categorised as a Read tool in the Synapse MCP Server, which means it retrieves data without modifying state.
Register the Synapse MCP server in PolicyLayer and add a rule for garden_read: 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.
garden_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the garden_read 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.
Set action: deny in the PolicyLayer policy for garden_read. 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.
garden_read 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →