garden_query

Use this for a PRECISE, structured search: multiple terms that must ALL be present (AND by default), field scopes (tag:, type:, folder:, path:), and OR / NOT operators. Triggers:

Server Synapse tomjrworks/synapse-obsidian
Category Read
Risk class Low
Parameters 00 required

What garden_query does on Synapse

AI agents call garden_query 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.

Why garden_query needs a policy

garden_query is a search and retrieval tool that queries the knowledge base without modifying, deleting, or executing external operations. It has read-only semantics comparable to database SELECT queries with filters. The blast radius of misuse is minimal—worst case returns unintended search results. Severity is low because it cannot alter data or trigger side effects beyond returning information.

From the tool's definition Tool performs 'PRECISE, structured search' with query operators (AND, OR, NOT) and field scopes (tag:, type:, folder:, path:). No mutations, deletions, or code execution mentioned. Retrieves matching notes from the Obsidian vault.

Questions about garden_query

What does the garden_query tool do? +

Use this for a PRECISE, structured search: multiple terms that must ALL be present (AND by default), field scopes (tag:, type:, folder:, path:), and OR / NOT operators. Triggers:. It is categorised as a Read tool in the Synapse MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on garden_query? +

Register the Synapse MCP server in PolicyLayer and add a rule for garden_query: 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.

What risk level is garden_query? +

garden_query is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit garden_query? +

Yes. Add a rate_limit block to the garden_query 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.

How do I block garden_query completely? +

Set action: deny in the PolicyLayer policy for garden_query. 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.

What MCP server provides garden_query? +

garden_query 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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.