Insert content into an existing note relative to a heading, block reference, or frontmatter field.
AI agents use patch_content to create or update resources in MCP server for Obsidian — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP server for Obsidian environment.
This tool creates or modifies data in a reversible manner (content can be edited or undone), which is the definition of Write. It is not Destructive because insertion is not irreversible deletion. It is not Execute because it does not run code or trigger external operations.
From the tool's definition Tool name is 'patch_content' and description states it 'Insert[s] content into an existing note' — this modifies existing data reversibly.
Documented attack patterns abuse exactly the kind of access patch_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP server for Obsidian, and nothing reaches the server without passing your rules. This is the rule we recommend for patch_content:
{
"version": "1",
"default": "deny",
"tools": {
"patch_content": {
"limits": [
{
"counter": "patch_content_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}patch_content 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.
Insert content into an existing note relative to a heading, block reference, or frontmatter field. It is categorised as a Write tool in the MCP server for Obsidian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP server for Obsidian MCP server in PolicyLayer and add a rule for patch_content: 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 MCP server for Obsidian. Nothing to install.
patch_content 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 patch_content 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 patch_content. 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.
patch_content is provided by the MCP server for Obsidian MCP server (markuspfundstein/mcp-obsidian). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP server for Obsidian, 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.
7 MCP server for Obsidian tools catalogued and risk-classified — across an index of 43,000+ MCP servers.