Critical Risk →

roam_delete_block

Delete a single block from the graph by its UID.

How to control roam_delete_block ↓

What roam_delete_block does on Roam Research MCP Server

AI agents call roam_delete_block to permanently remove resources in Roam Research MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why roam_delete_block needs a policy

This tool irreversibly removes data from the user's knowledge graph. While deletion of a single block may have limited blast radius compared to bulk deletion, it is still a destructive action that cannot be reversed programmatically. An AI agent with access could maliciously or mistakenly delete important content blocks.

From the tool's definition Tool name 'roam_delete_block' combined with description 'Delete a single block from the graph by its UID' explicitly performs irreversible deletion of data.

Documented attack patterns abuse exactly the kind of access roam_delete_block gives an agent:

How to control roam_delete_block

PolicyLayer is an MCP gateway — it sits between your AI agents and Roam Research MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for roam_delete_block:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "roam_delete_block"
  ]
}

roam_delete_block disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Roam Research MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about roam_delete_block

What does the roam_delete_block tool do? +

Delete a single block from the graph by its UID. It is categorised as a Destructive tool in the Roam Research MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on roam_delete_block? +

Register the Roam Research MCP Server MCP server in PolicyLayer and add a rule for roam_delete_block: 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 Roam Research MCP Server. Nothing to install.

What risk level is roam_delete_block? +

roam_delete_block is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit roam_delete_block? +

Yes. Add a rate_limit block to the roam_delete_block 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.

How do I block roam_delete_block completely? +

Set action: deny in the PolicyLayer policy for roam_delete_block. 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.

What MCP server provides roam_delete_block? +

roam_delete_block is provided by the Roam Research MCP Server MCP server (philosolares/roam-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Roam Research MCP Server tool call.

Start from Roam Research 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.

26 Roam Research MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.