Full-text search in note content. Use dataview_query instead for structured queries (by frontmatter, tags, folders, dates).
AI agents call vault_search to retrieve information from Connect MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs full-text search across note content in an Obsidian vault, which is a query/retrieval operation with no side effects. It does not create, modify, delete, or execute anything—it simply returns search results from existing notes. This is a classic Read operation.
From the tool's definition Tool name 'vault_search' combined with description stating 'Full-text search in note content' indicates retrieval of data without modification.
Attacks that exploit this kind of access
Full-text search in note content. Use dataview_query instead for structured queries (by frontmatter, tags, folders, dates). It is categorised as a Read tool in the Connect MCP MCP Server, which means it retrieves data without modifying state.
Register the Connect MCP server in PolicyLayer and add a rule for vault_search: 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 Connect MCP. Nothing to install.
vault_search 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 vault_search 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 vault_search. 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.
vault_search is provided by the Connect MCP server (joch/obsidian-connect-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 →