LEGACY shortcut. Use only when the user wants a one-call scaffold of a structured knowledge base on a specific topic (sources/, notes/, outputs/, CLAUDE.md, index.md, config) and is willing to skip the option-A/B/C choice. For most users, prefer \
AI agents use taproot_sow to create or update resources in Synapse — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Synapse environment.
This tool creates a structured set of files and folders (scaffold) in the user's vault. It writes new content (directories, markdown files, config) but does not delete or overwrite existing data irreversibly, nor does it execute code or involve finances. The blast radius is medium because it could create unwanted directory structures and files across the vault, but these are reversible.
From the tool's definition 'one-call scaffold of a structured knowledge base on a specific topic (sources/, notes/, outputs/, CLAUDE.md, index.md, config)' — creates multiple files and directory structures in the Obsidian vault
Attacks that exploit this kind of access
LEGACY shortcut. Use only when the user wants a one-call scaffold of a structured knowledge base on a specific topic (sources/, notes/, outputs/, CLAUDE.md, index.md, config) and is willing to skip the option-A/B/C choice. For most users, prefer \. It is categorised as a Write tool in the Synapse MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Synapse MCP server in PolicyLayer and add a rule for taproot_sow: 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_sow is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the taproot_sow 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_sow. 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_sow 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 →