collections_delete
Delete a knowledge collection. If the collection is assigned to agents, prompts, or channels, pass force=true to delete anyway. CASCADE removes all assignments automatically.
This record as markdown: /tools/io-github-saloprj-dialogbrain/collections-delete.md
What collections_delete does on Dialogbrain
AI agents call collections_delete to permanently remove resources in Dialogbrain, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
force | boolean | — | Force delete even if collection is in use. OMIT for the safe default (refuse to delete in-use collections). |
collection_id | integer | Yes | ID of the collection to delete |
Parameters from the server's own tool schema.
Why collections_delete is rated Critical
The tool irreversibly deletes a knowledge collection and can cascade-delete all associated assignments to agents, prompts, and channels. This is a destructive operation that cannot be undone and could result in loss of important data and configuration. The force flag and CASCADE behavior indicate the tool can cause widespread deletion effects.
From the tool's definition Delete a knowledge collection. If the collection is assigned to agents, prompts, or channels, pass force=true to delete anyway. CASCADE removes all assignments automatically.
Attacks that exploit this kind of access
The rule that runs collections_delete safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For collections_delete, this is the rule to start with:
collections_delete is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every collections_delete call is checked against it from then on.
Questions about collections_delete
Delete a knowledge collection. If the collection is assigned to agents, prompts, or channels, pass force=true to delete anyway. CASCADE removes all assignments automatically. It is categorised as a Destructive tool in the Dialogbrain MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
collections_delete accepts 2 parameters: force, collection_id. Required: collection_id. The full parameter table on this page comes from the server's own tool schema.
Register the Dialogbrain MCP server in PolicyLayer and add a rule for collections_delete: 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 Dialogbrain. Nothing to install.
collections_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the collections_delete 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 collections_delete. 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.
collections_delete is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dialogbrain, and thousands of servers like it.
Across the catalogue