Return the parsed contents of a Base file: filters, properties, view definitions, and any unrecognized fields. Use to discover what queries a Base supports before calling query_base.
AI agents call read_base to retrieve information from Obsidian Mcp Pro without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and parses data from a Base file to expose its structure (filters, properties, view definitions). It performs no modifications, deletions, or external operations. The purpose is informational — to help understand what can be queried — making it a straightforward Read category tool with low severity impact.
From the tool's definition Tool description states 'Return the parsed contents of a Base file' and 'Use to discover what queries a Base supports' — both indicate retrieval without modification.
Documented attack patterns abuse exactly the kind of access read_base gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Obsidian Mcp Pro, and nothing reaches the server without passing your rules. This is the rule we recommend for read_base:
{
"version": "1",
"default": "deny",
"tools": {
"read_base": {}
}
} read_base is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Return the parsed contents of a Base file: filters, properties, view definitions, and any unrecognized fields. Use to discover what queries a Base supports before calling query_base. It is categorised as a Read tool in the Obsidian Mcp Pro MCP Server, which means it retrieves data without modifying state.
Register the Obsidian Mcp Pro MCP server in PolicyLayer and add a rule for read_base: 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 Pro. Nothing to install.
read_base 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 read_base 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 read_base. 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.
read_base is provided by the Obsidian Mcp Pro MCP server (rps321321/obsidian-mcp-pro). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Obsidian Mcp Pro, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
41 Obsidian Mcp Pro tools catalogued and risk-classified — across an index of 43,000+ MCP servers.