collections_remove_file
Remove a file from a knowledge collection. The file itself is not deleted — only the collection membership is removed.
This record as markdown: /tools/io-github-saloprj-dialogbrain/collections-remove-file.md
What collections_remove_file does on Dialogbrain
AI agents use collections_remove_file to create or update resources in Dialogbrain, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dialogbrain environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
file_id | integer | Yes | ID of the file to remove |
collection_id | integer | Yes | ID of the collection |
Parameters from the server's own tool schema.
Why collections_remove_file is rated Medium
This tool modifies collection membership by removing a file from a collection, but explicitly does not delete the file itself. The action is a reversible write operation (the file can be re-added), not a destructive one. Misuse could disrupt AI agent knowledge bases by removing important files from collections.
From the tool's definition 'Remove a file from a knowledge collection' and 'The file itself is not deleted — only the collection membership is removed.'
Attacks that exploit this kind of access
The rule that runs collections_remove_file 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_remove_file, this is the rule to start with:
collections_remove_file 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every collections_remove_file call is checked against it from then on.
Questions about collections_remove_file
Remove a file from a knowledge collection. The file itself is not deleted — only the collection membership is removed. It is categorised as a Write tool in the Dialogbrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
collections_remove_file accepts 2 parameters: file_id, collection_id. Required: file_id, 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_remove_file: 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_remove_file 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 collections_remove_file 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_remove_file. 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_remove_file 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.
This server
Across the catalogue