AI agents use keychain_disconnect to create or update resources in UnClick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
label | string | — | Label of the credential to remove. Omit to remove all labels for the platform. |
platform | string | Yes | Platform ID to disconnect: github, supabase, vercel, stripe, cloudflare. |
Parameters from the server's own tool schema.
This is classified as Write rather than Destructive because credential removal from a keychain is typically reversible—the user can re-authenticate and re-add credentials. It modifies the caller's own credential store (scoped to their UNCLICK_API_KEY) without permanently destroying underlying platform accounts.
From the tool's definition The tool description states it will 'Remove a platform credential from the UnClick Keychain,' which modifies stored authentication data by deleting/removing credentials.
Attacks that exploit this kind of access
Remove a platform credential from the UnClick Keychain. Scoped to the caller's UNCLICK_API_KEY. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
keychain_disconnect accepts 2 parameters: label, platform. Required: platform. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for keychain_disconnect: 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 UnClick. Nothing to install.
keychain_disconnect 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 keychain_disconnect 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 keychain_disconnect. 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.
keychain_disconnect is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →