AI agents call read_file to retrieve information from Obsidian HTTP MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves file content from Obsidian without modifying, deleting, or executing anything. It is a straightforward read operation with minimal security risk—the only concern would be unauthorized access to sensitive note contents, but that is inherent to any read operation and does not constitute a higher-severity category.
From the tool's definition Tool name is 'read_file' and description states 'Read content of a file.' This is a retrieval operation with no side effects on the data.
Documented attack patterns abuse exactly the kind of access read_file gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Obsidian HTTP MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for read_file:
{
"version": "1",
"default": "deny",
"tools": {
"read_file": {}
}
}read_file 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.
Read content of a file. TIP: If you don\. It is categorised as a Read tool in the Obsidian HTTP MCP MCP Server, which means it retrieves data without modifying state.
Register the Obsidian HTTP MCP server in PolicyLayer and add a rule for read_file: 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 HTTP MCP. Nothing to install.
read_file 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_file 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_file. 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_file is provided by the Obsidian HTTP MCP server (nasandnora/obsidian-http-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Obsidian HTTP MCP, 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.
12 Obsidian HTTP MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.