credentials_delete
Remove a stored credential by service and key. The encrypted store file is rewritten without the deleted entry.
This record as markdown: /tools/io-github-aibtcdev-mcp-server/credentials-delete.md
What credentials_delete does on Aibtc
AI agents call credentials_delete to permanently remove resources in Aibtc, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why credentials_delete is rated Critical
The tool permanently deletes credential entries from an encrypted credential store. This is an irreversible operation that destroys data (credentials cannot be recovered after deletion). Although the blast radius is somewhat limited to stored credentials rather than application data, deletion operations fall under the Destructive category by definition.
From the tool's definition Tool description states 'Remove a stored credential' and 'encrypted store file is rewritten without the deleted entry' — irreversible deletion of data from persistent storage.
Attacks that exploit this kind of access
The rule that runs credentials_delete safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Aibtc, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For credentials_delete, this is the rule to start with:
credentials_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 Aibtc, apply this rule, and every credentials_delete call is checked against it from then on.
Questions about credentials_delete
Remove a stored credential by service and key. The encrypted store file is rewritten without the deleted entry. It is categorised as a Destructive tool in the Aibtc MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Aibtc MCP server in PolicyLayer and add a rule for credentials_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 Aibtc. Nothing to install.
credentials_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 credentials_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 credentials_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.
credentials_delete is provided by the Aibtc MCP server (aibtcdev/aibtc-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Aibtc, and thousands of servers like it.
Across the catalogue