Create a directed edge connecting two existing canvas nodes. Both fromNode and toNode must already exist on the canvas (use read_canvas to list node ids, or capture the id returned by add_canvas_node). Optional fromSide/toSide control which face of each node the edge anchors to. Returns the gener...
AI agents use add_canvas_edge to create or update resources in Obsidian Mcp Pro — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Obsidian Mcp Pro environment.
This tool creates a new relationship object (edge) between existing nodes in a canvas. It is a reversible modification operation (edges can be deleted), with no side effects beyond adding data to the canvas structure. It does not execute code, delete data, or affect external systems. While it modifies canvas state, the blast radius is limited to the canvas document itself and the change can be undone.
From the tool's definition Tool description states 'Create a directed edge connecting two existing canvas nodes' and 'Returns the generated edge UUID'. This is creating/adding a new connection object in a canvas data structure.
Documented attack patterns abuse exactly the kind of access add_canvas_edge 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 add_canvas_edge:
{
"version": "1",
"default": "deny",
"tools": {
"add_canvas_edge": {
"limits": [
{
"counter": "add_canvas_edge_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_canvas_edge stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a directed edge connecting two existing canvas nodes. Both fromNode and toNode must already exist on the canvas (use read_canvas to list node ids, or capture the id returned by add_canvas_node). Optional fromSide/toSide control which face of each node the edge anchors to. Returns the generated edge UUID. It is categorised as a Write tool in the Obsidian Mcp Pro MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Obsidian Mcp Pro MCP server in PolicyLayer and add a rule for add_canvas_edge: 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.
add_canvas_edge is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_canvas_edge 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 add_canvas_edge. 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.
add_canvas_edge 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.