AI agents call read_canvas to retrieve information from Obsidian MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation on canvas data structures within an Obsidian vault. It retrieves and parses information without creating, modifying, deleting, or executing any code. The absence of action verbs like 'create', 'update', 'delete', or 'execute' confirms it is a safe Read operation with minimal blast radius if misused.
From the tool's definition Tool name is 'read_canvas' and description states 'Parse and read canvas structure' — both indicate retrieval/parsing of existing data with no modification or side effects.
Documented attack patterns abuse exactly the kind of access read_canvas gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Obsidian MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for read_canvas:
{
"version": "1",
"default": "deny",
"tools": {
"read_canvas": {}
}
}read_canvas 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.
Parse and read canvas structure. It is categorised as a Read tool in the Obsidian MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Obsidian MCP Server MCP server in PolicyLayer and add a rule for read_canvas: 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 Server. Nothing to install.
read_canvas 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_canvas 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_canvas. 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_canvas is provided by the Obsidian MCP Server MCP server (kynlos/obsidian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Obsidian MCP Server, 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.
120 Obsidian MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.