wiki_query
AI agents call wiki_query to retrieve information from Obsidian Mcp Fast without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the context—a high-performance retrieval server for Obsidian vaults with sibling tools named 'wiki_read' and 'wiki_stats'—strongly indicates this is a query/search tool for retrieving note data without side effects. The server's stated purpose is 'retrieval of notes' with no mention of modification or deletion.
From the tool's definition Tool name is 'wiki_query' and server description indicates 'retrieval of notes' as a core function. Sibling tool 'wiki_read' confirms read-only capabilities. Empty tool description lowers confidence slightly.
Attacks that exploit this kind of access
wiki_query. It is categorised as a Read tool in the Obsidian Mcp Fast MCP Server, which means it retrieves data without modifying state.
Register the Obsidian Mcp Fast MCP server in PolicyLayer and add a rule for wiki_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 Obsidian Mcp Fast. Nothing to install.
wiki_query 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 wiki_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.
Set action: deny in the PolicyLayer policy for wiki_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.
wiki_query is provided by the Obsidian Mcp Fast MCP server (thedavidquan01/obsidian-mcp-fast). 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 →