Use this whenever the user references a note by a code or identifier — a course code, PR number, version, ticket. Returns notes whose tokens contain that exact identifier (digit-bearing), and on a miss suggests close identifiers in the vault. Triggers:
AI agents call garden_identifier 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.
garden_identifier retrieves and queries data from the Obsidian vault without side effects. It performs pattern matching on note tokens and returns results or suggestions, which is a standard read operation. No data is created, modified, deleted, or executed. Even as a sibling to destructive tools like garden_delete, this tool's scope is clearly limited to search and retrieval.
From the tool's definition Tool is explicitly designed to search and return notes by identifier/code matching. Description states it 'Returns notes whose tokens contain that exact identifier' and 'suggests close identifiers' — both retrieval-only operations with no modification or…
Attacks that exploit this kind of access
Use this whenever the user references a note by a code or identifier — a course code, PR number, version, ticket. Returns notes whose tokens contain that exact identifier (digit-bearing), and on a miss suggests close identifiers in the vault. 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_identifier: 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_identifier 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_identifier 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_identifier. 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_identifier 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 →