AI agents call taproot_prune 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 name 'prune' suggesting potential destructive action, the description clearly indicates this tool performs read-only analysis and reporting. It audits vault structure and content, identifies issues, and suggests fixes without actually modifying or deleting data. This is consistent with diagnostic/query operations. No side effects or data mutations occur.
From the tool's definition The tool description states it 'Returns a report and suggested fixes' for vault quality issues like 'broken links, orphan pages, missing frontmatter, stale content.' The language indicates inspection and analysis ('quality audit', 'report') with no…
Attacks that exploit this kind of access
Use this whenever the user wants a quality audit of their vault — broken links, orphan pages, missing frontmatter, stale content. Returns a report and suggested fixes. 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 taproot_prune: 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.
taproot_prune 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 taproot_prune 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 taproot_prune. 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.
taproot_prune 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 →