AI agents call garden_backlinks 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.
The garden_backlinks tool performs a search/retrieval operation across the Obsidian vault to discover relationships between notes. It has no side effects, does not create, modify, delete, or execute operations. The operation is read-only and returns information about existing note structure.
From the tool's definition Tool description states it finds notes that 'contain a [[wikilink]] pointing at a target note' — this is a query operation that retrieves and lists inbound link references without modifying data.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Use this to find every note whose body contains a [[wikilink]] pointing at a target note — its inbound links /. 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_backlinks: 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_backlinks 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_backlinks 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_backlinks. 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_backlinks 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 →