Intelligently update existing notes with multiple modes: append, append_section (add new section), update_section (update specific section), merge, replace, frontmatter only, or consolidate (merge children back into hub). Maintains version tracking and auto-links new content.
AI agents use palace_improve to create or update resources in Obsidian Palace MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Obsidian Palace MCP environment.
This tool modifies existing notes in multiple ways including full replacement and merging. While version tracking suggests some reversibility, 'replace' and 'consolidate' modes could overwrite significant content. It spans Write and potentially Destructive territory, but version tracking keeps it in Write. High severity because an AI agent could overwrite or corrupt important vault notes at scale.
From the tool's definition update existing notes with multiple modes: append, append_section, update_section, merge, replace, frontmatter only, or consolidate — Maintains version tracking
Attacks that exploit this kind of access
Intelligently update existing notes with multiple modes: append, append_section (add new section), update_section (update specific section), merge, replace, frontmatter only, or consolidate (merge children back into hub). Maintains version tracking and auto-links new content. It is categorised as a Write tool in the Obsidian Palace MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Obsidian Palace MCP server in PolicyLayer and add a rule for palace_improve: 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 Obsidian Palace MCP. Nothing to install.
palace_improve 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 palace_improve 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 palace_improve. 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.
palace_improve is provided by the Obsidian Palace MCP server (probably-computers/obsidian-palace-mcp). 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 →