CONTEXT LOADING: When a session opens with a message that references a project, prior work, a topic, or anything implying continuity — even implicitly — call garden_find immediately before responding. Intent-based, not phrase-based; don
AI agents call garden_find 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_find retrieves contextual information from an Obsidian vault to inform responses. This is a search/retrieval operation with no side effects, matching the Read category. The incomplete description ('don' appears truncated) limits confidence slightly, but the clear intent is querying/loading data rather than modifying or executing operations.
From the tool's definition Tool description indicates it performs context loading and retrieval operations: 'call garden_find immediately before responding' to load prior work and topics. No modification, deletion, or execution of external operations described.
Attacks that exploit this kind of access
CONTEXT LOADING: When a session opens with a message that references a project, prior work, a topic, or anything implying continuity — even implicitly — call garden_find immediately before responding. Intent-based, not phrase-based; don. 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_find: 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_find 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_find 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_find. 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_find 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 →