AI agents call garden_survey 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.
Despite the truncated description, 'survey' semantically indicates inspection or overview of data without modification. The server context (Obsidian vault querying) and sibling tools like 'garden_query', 'garden_find', and 'garden_forage' all suggest read-only exploration. No evidence of side effects, deletion, or modification. Confidence is moderate due to incomplete description.
From the tool's definition Tool name 'garden_survey' and context suggest viewing/inspection functionality. Description is incomplete ('Use this whenever the user wants to see what') but the pattern of sibling tools and the framing of 'survey' as observational implies data retrieval.
Attacks that exploit this kind of access
Use this whenever the user wants to see what. 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_survey: 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_survey 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_survey 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_survey. 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_survey 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 →