Check for existing knowledge before creating new notes. Returns matches, domain suggestions, and a recommendation. ALWAYS call before palace_store to: 1. Find existing knowledge on the topic 2. Get domain suggestions based on vault structure 3. Determine best action (create_new, expand_stub, impr...
AI agents call palace_check to retrieve information from Obsidian Palace MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
palace_check performs retrieval and analysis of existing vault data to inform decision-making. It produces no modifications, deletions, or irreversible changes. The recommendation output is advisory only. This is a straightforward Read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool queries existing knowledge and returns matches, suggestions, and recommendations. The description states it 'Find[s] existing knowledge', 'Get[s] domain suggestions', and 'Determine[s] best action' — all read operations with no side effects.
Attacks that exploit this kind of access
Check for existing knowledge before creating new notes. Returns matches, domain suggestions, and a recommendation. ALWAYS call before palace_store to: 1. Find existing knowledge on the topic 2. Get domain suggestions based on vault structure 3. Determine best action (create_new, expand_stub, improve_existing, reference_existing) Domain suggestions help you choose the right path for new knowledge based on existing vault organization. Use path_filter to focus on a specific domain area (e.g.,. It is categorised as a Read tool in the Obsidian Palace MCP MCP Server, which means it retrieves data without modifying state.
Register the Obsidian Palace MCP server in PolicyLayer and add a rule for palace_check: 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_check 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 palace_check 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_check. 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_check 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 →